borgr commited on
Commit
a937004
β€’
1 Parent(s): 9b28f49

## What are you reporting:
**Contaminated model(s)**: GPT-4

**Contaminated corpora**:
conll2003
nyu-mll/glue
rajpurkar/squad_v2
https://catalog.ldc.upenn.edu/LDC2006T06
quac;;GPT-4;Model
natural_questions
google/boolq
**Contaminated split(s)**: If the dataset has Train, Development and/or Test splits please report the contaminated split(s). You can report a percentage of the dataset contaminated; if the entire dataset is compromised, report 100%.
It is unclear what is the percentage, we just know the model regurgitates training validataion and test data and or metadata of each.

> You may also report instances where there is no contamination. In such cases, follow the previous instructions but report a contamination level of 0%.

## Briefly describe your method to detect data contamination

- [ ] Model-based approach

Description of your method, 3-4 sentences. Evidence of data contamination (Read below):
Prompt GPT and see that it knows to return metadata and training and val\test examples on its own.
see more here
https://hitz-zentroa.github.io/lm-contamination/blog/

#### Data-based approaches
Data-based approaches identify evidence of data contamination in a pre-training corpus by directly examining the dataset for instances of the evaluation data. This method involves algorithmically searching through a large pre-training dataset to find occurrences of the evaluation data. You should provide evidence of data contamination in the form: "dataset X appears in line N of corpus Y," "dataset X appears N times in corpus Y," or "N examples from dataset X appear in corpus Y."

#### Model-based approaches

Model-based approaches, on the other hand, utilize heuristic algorithms to infer the presence of data contamination in a pre-trained model. These methods do not directly analyze the data but instead assess the model's behavior to predict data contamination. Examples include prompting the model to reproduce elements of an evaluation dataset to demonstrate memorization (i.e https://hitz-zentroa.github.io/lm-contamination/blog/) or using perplexity measures to estimate data contamination (). You should provide evidence of data contamination in the form of evaluation results of the algorithm from research papers, screenshots of model outputs that demonstrate memorization of a pre-training dataset, or any other form of evaluation that substantiates the method's effectiveness in detecting data contamination. You can provide a confidence score in your predictions.

## Citation

Is there a paper that reports the data contamination or describes the method used to detect data contamination?
Blog post not paper, so we can create a bib if we want
URL: `[https://aclanthology.org/2023.findings-emnlp.722/](https://hitz-zentroa.github.io/lm-contamination/blog/)`
Citation: `@inproceedings{...`


*Important!* If you wish to be listed as an author in the final report, please complete this information for all the authors of this Pull Request.
- Full name: Leshem Choshen
- Institution: MIT-IBM watson AI lab, MIT
- Email: leshem.choshen@mail.huji.ac.il

Files changed (1) hide show
  1. contamination_report.csv +214 -206
contamination_report.csv CHANGED
@@ -1,5 +1,12 @@
1
  Evaluation Dataset;Subset;Contaminated Source;Model or corpus;Train Split;Development Split;Test Split;Approach;Reference;PR
2
-
 
 
 
 
 
 
 
3
  lama;T-REx;allenai/c4;corpus;;;4.6;data-based;https://arxiv.org/abs/2104.08758;6
4
  lama;Google-RE;allenai/c4;corpus;;;5.7;data-based;https://arxiv.org/abs/2104.08758;6
5
  EdinburghNLP/xsum;;allenai/c4;corpus;;;15.49;data-based;https://arxiv.org/abs/2104.08758;6
@@ -15,9 +22,9 @@ nyu-mll/glue;MRPC-sentence-1;allenai/c4;corpus;;;2.7;data-based;https://arxiv.or
15
  nyu-mll/glue;MRPC-sentence-2;allenai/c4;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
16
  nyu-mll/glue;QNLI-sentence;allenai/c4;corpus;;;53.6;data-based;https://arxiv.org/abs/2104.08758;6
17
  nyu-mll/glue;QNLI-question;allenai/c4;corpus;;;1.8;data-based;https://arxiv.org/abs/2104.08758;6
18
- nyu-mll/glue;RTE-sentence-1;allenai/c4;corpus;;;6.0;data-based;https://arxiv.org/abs/2104.08758;6
19
  nyu-mll/glue;RTE-sentence-2;allenai/c4;corpus;;;10.8;data-based;https://arxiv.org/abs/2104.08758;6
20
- nyu-mll/glue;SST-2;allenai/c4;corpus;;;11.0;data-based;https://arxiv.org/abs/2104.08758;6
21
  nyu-mll/glue;STS-B-sentence-1;allenai/c4;corpus;;;18.3;data-based;https://arxiv.org/abs/2104.08758;6
22
  nyu-mll/glue;STS-B-sentence-2;allenai/c4;corpus;;;18.6;data-based;https://arxiv.org/abs/2104.08758;6
23
  nyu-mll/glue;WNLI-sentence-1;allenai/c4;corpus;;;4.8;data-based;https://arxiv.org/abs/2104.08758;6
@@ -28,20 +35,20 @@ UCLNLP/adversarial_qa;adversarialQA;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-b
28
  UCLNLP/adversarial_qa;adversarialQA;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
29
  UCLNLP/adversarial_qa;adversarialQA;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
30
 
31
- UCLNLP/adversarial_qa;dbert;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
32
- UCLNLP/adversarial_qa;dbert;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
33
- UCLNLP/adversarial_qa;dbert;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
34
- UCLNLP/adversarial_qa;dbert;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
35
 
36
- UCLNLP/adversarial_qa;dbidaf;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
37
- UCLNLP/adversarial_qa;dbidaf;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
38
- UCLNLP/adversarial_qa;dbidaf;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
39
- UCLNLP/adversarial_qa;dbidaf;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
40
 
41
  UCLNLP/adversarial_qa;droberta;allenai/c4;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
42
  UCLNLP/adversarial_qa;droberta;oscar-corpus/OSCAR-2301;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
43
  UCLNLP/adversarial_qa;droberta;EleutherAI/pile;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
44
- UCLNLP/adversarial_qa;droberta;togethercomputer/RedPajama-Data-V2;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707
45
 
46
  aeslc;;allenai/c4;corpus;;;1.57;data-based;https://arxiv.org/abs/2310.20707;2
47
  aeslc;;oscar-corpus/OSCAR-2301;corpus;;;0.31;data-based;https://arxiv.org/abs/2310.20707;2
@@ -49,7 +56,7 @@ aeslc;;EleutherAI/pile;corpus;;;45.49;data-based;https://arxiv.org/abs/2310.2070
49
  aeslc;;togethercomputer/RedPajama-Data-V2;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
50
 
51
  amazon_reviews_multi;;allenai/c4;corpus;;;2.28;data-based;https://arxiv.org/abs/2310.20707;2
52
- amazon_reviews_multi;;oscar-corpus/OSCAR-2301;corpus;;;2.10;data-based;https://arxiv.org/abs/2310.20707;2
53
  amazon_reviews_multi;;EleutherAI/pile;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;2
54
  amazon_reviews_multi;;togethercomputer/RedPajama-Data-V2;corpus;;;2.06;data-based;https://arxiv.org/abs/2310.20707;2
55
 
@@ -58,23 +65,23 @@ billsum;;oscar-corpus/OSCAR-2301;corpus;;;0.06;data-based;https://arxiv.org/abs/
58
  billsum;;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
59
  billsum;;togethercomputer/RedPajama-Data-V2;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
60
 
61
- cosmos_qa;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
62
- cosmos_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
63
- cosmos_qa;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
64
- cosmos_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
65
 
66
- crows_pairs;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
67
  crows_pairs;;oscar-corpus/OSCAR-2301;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
68
- crows_pairs;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
69
- crows_pairs;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
70
 
71
- ibm/duorc;ParaphraseRC;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
72
- ibm/duorc;ParaphraseRC;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
73
- ibm/duorc;ParaphraseRC;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
74
- ibm/duorc;ParaphraseRC;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
75
 
76
  ibm/duorc;SelfRC;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
77
- ibm/duorc;SelfRC;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
78
  ibm/duorc;SelfRC;EleutherAI/pile;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
79
  ibm/duorc;SelfRC;togethercomputer/RedPajama-Data-V2;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
80
 
@@ -104,7 +111,7 @@ nyu-mll/glue;mnli-mismatched;EleutherAI/pile;corpus;;;2.11;data-based;https://ar
104
  nyu-mll/glue;mnli-mismatched;togethercomputer/RedPajama-Data-V2;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;2
105
 
106
  nyu-mll/glue;mrpc;allenai/c4;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
107
- nyu-mll/glue;mrpc;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
108
  nyu-mll/glue;mrpc;EleutherAI/pile;corpus;;;0.64;data-based;https://arxiv.org/abs/2310.20707;2
109
  nyu-mll/glue;mrpc;togethercomputer/RedPajama-Data-V2;corpus;;;1.16;data-based;https://arxiv.org/abs/2310.20707;2
110
 
@@ -113,7 +120,7 @@ nyu-mll/glue;qnli;oscar-corpus/OSCAR-2301;corpus;;;0.04;data-based;https://arxiv
113
  nyu-mll/glue;qnli;EleutherAI/pile;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;2
114
  nyu-mll/glue;qnli;togethercomputer/RedPajama-Data-V2;corpus;;;1.21;data-based;https://arxiv.org/abs/2310.20707;2
115
 
116
- nyu-mll/glue;rte;allenai/c4;corpus;;;0.20;data-based;https://arxiv.org/abs/2310.20707;2
117
  nyu-mll/glue;rte;oscar-corpus/OSCAR-2301;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;2
118
  nyu-mll/glue;rte;EleutherAI/pile;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
119
  nyu-mll/glue;rte;togethercomputer/RedPajama-Data-V2;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;2
@@ -123,9 +130,9 @@ nyu-mll/glue;stsb;oscar-corpus/OSCAR-2301;corpus;;;3.12;data-based;https://arxiv
123
  nyu-mll/glue;stsb;EleutherAI/pile;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;2
124
  nyu-mll/glue;stsb;togethercomputer/RedPajama-Data-V2;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;2
125
 
126
- nyu-mll/glue;wnli;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
127
- nyu-mll/glue;wnli;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
128
- nyu-mll/glue;wnli;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
129
  nyu-mll/glue;wnli;togethercomputer/RedPajama-Data-V2;corpus;;;2.05;data-based;https://arxiv.org/abs/2310.20707;2
130
 
131
  head_qa;en;allenai/c4;corpus;;;5.22;data-based;https://arxiv.org/abs/2310.20707;2
@@ -134,57 +141,57 @@ head_qa;en;EleutherAI/pile;corpus;;;5.11;data-based;https://arxiv.org/abs/2310.2
134
  head_qa;en;togethercomputer/RedPajama-Data-V2;corpus;;;5.94;data-based;https://arxiv.org/abs/2310.20707;2
135
 
136
  health_fact;;allenai/c4;corpus;;;7.53;data-based;https://arxiv.org/abs/2310.20707;2
137
- health_fact;;oscar-corpus/OSCAR-2301;corpus;;;3.40;data-based;https://arxiv.org/abs/2310.20707;2
138
  health_fact;;EleutherAI/pile;corpus;;;1.94;data-based;https://arxiv.org/abs/2310.20707;2
139
- health_fact;;togethercomputer/RedPajama-Data-V2;corpus;;;18.70;data-based;https://arxiv.org/abs/2310.20707;2
140
 
141
- hlgd;;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
142
- hlgd;;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
143
- hlgd;;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
144
- hlgd;;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
145
 
146
  liar;;allenai/c4;corpus;;;29.23;data-based;https://arxiv.org/abs/2310.20707;2
147
  liar;;oscar-corpus/OSCAR-2301;corpus;;;13.95;data-based;https://arxiv.org/abs/2310.20707;2
148
  liar;;EleutherAI/pile;corpus;;;10.91;data-based;https://arxiv.org/abs/2310.20707;2
149
  liar;;togethercomputer/RedPajama-Data-V2;corpus;;;45.05;data-based;https://arxiv.org/abs/2310.20707;2
150
 
151
- math_dataset;algebra__linear_1d;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
152
- math_dataset;algebra__linear_1d;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
153
- math_dataset;algebra__linear_1d;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
154
- math_dataset;algebra__linear_1d;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
155
 
156
- math_dataset;algebra__linear_2d;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
157
- math_dataset;algebra__linear_2d;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
158
- math_dataset;algebra__linear_2d;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
159
- math_dataset;algebra__linear_2d;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
160
 
161
- math_dataset;algebra__linear_2d_composed;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
162
- math_dataset;algebra__linear_2d_composed;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
163
- math_dataset;algebra__linear_2d_composed;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
164
- math_dataset;algebra__linear_2d_composed;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
165
 
166
  math_qa;;allenai/c4;corpus;;;0.34;data-based;https://arxiv.org/abs/2310.20707;2
167
  math_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
168
- math_qa;;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
169
  math_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.07;data-based;https://arxiv.org/abs/2310.20707;2
170
 
171
- mc_taco;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
172
- mc_taco;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
173
- mc_taco;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
174
  mc_taco;;togethercomputer/RedPajama-Data-V2;corpus;;;0.14;data-based;https://arxiv.org/abs/2310.20707;2
175
 
176
- mocha;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
177
- mocha;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
178
- mocha;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
179
- mocha;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
180
 
181
- openai_humaneval;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
182
  openai_humaneval;;oscar-corpus/OSCAR-2301;corpus;;;1.22;data-based;https://arxiv.org/abs/2310.20707;2
183
- openai_humaneval;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
184
- openai_humaneval;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
185
 
186
  paws-x;en;allenai/c4;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;2
187
- paws-x;en;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
188
  paws-x;en;EleutherAI/pile;corpus;;;0.15;data-based;https://arxiv.org/abs/2310.20707;2
189
  paws-x;en;togethercomputer/RedPajama-Data-V2;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
190
 
@@ -200,247 +207,248 @@ piqa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.13;data-based;https://arxiv.
200
 
201
  race;all;allenai/c4;corpus;;;0.14;data-based;https://arxiv.org/abs/2310.20707;2
202
  race;all;oscar-corpus/OSCAR-2301;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
203
- race;all;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
204
  race;all;togethercomputer/RedPajama-Data-V2;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
205
 
206
  race;high;allenai/c4;corpus;;;0.11;data-based;https://arxiv.org/abs/2310.20707;2
207
- race;high;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
208
- race;high;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
209
  race;high;togethercomputer/RedPajama-Data-V2;corpus;;;0.26;data-based;https://arxiv.org/abs/2310.20707;2
210
 
211
  race;middle;allenai/c4;corpus;;;0.21;data-based;https://arxiv.org/abs/2310.20707;2
212
  race;middle;oscar-corpus/OSCAR-2301;corpus;;;0.21;data-based;https://arxiv.org/abs/2310.20707;2
213
- race;middle;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
214
  race;middle;togethercomputer/RedPajama-Data-V2;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;2
215
 
216
- allenai/ropes;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
217
- allenai/ropes;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
218
- allenai/ropes;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
219
- allenai/ropes;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
220
 
221
- samsum;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
222
- samsum;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
223
- samsum;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
224
  samsum;;togethercomputer/RedPajama-Data-V2;corpus;;;0.12;data-based;https://arxiv.org/abs/2310.20707;2
225
 
226
- scan;addprim_jump;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
227
- scan;addprim_jump;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
228
  scan;addprim_jump;EleutherAI/pile;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;2
229
  scan;addprim_jump;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;2
230
 
231
- scan;addprim_turn;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
232
- scan;addprim_turn;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
233
  scan;addprim_turn;EleutherAI/pile;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;2
234
- scan;addprim_turn;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
235
-
236
- scan;filler_num0;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
237
- scan;filler_num0;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
238
- scan;filler_num0;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
239
  scan;filler_num0;togethercomputer/RedPajama-Data-V2;corpus;;;0.9;data-based;https://arxiv.org/abs/2310.20707;2
240
-
241
- scan;length;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
242
- scan;length;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
243
  scan;length;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
244
- scan;length;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
245
-
246
  scan;simple;allenai/c4;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
247
- scan;simple;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
248
  scan;simple;EleutherAI/pile;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
249
  scan;simple;togethercomputer/RedPajama-Data-V2;corpus;;;0.26;data-based;https://arxiv.org/abs/2310.20707;2
250
-
251
- scan;template_around;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
252
- scan;template_around;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
253
- scan;template_around;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
254
  scan;template_around;togethercomputer/RedPajama-Data-V2;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
255
-
256
- scan;template_jump;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
257
- scan;template_jump;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
258
- scan;template_jump;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
259
  scan;template_jump;togethercomputer/RedPajama-Data-V2;corpus;;;0.9;data-based;https://arxiv.org/abs/2310.20707;2
260
-
261
- scan;template_opposite;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
262
- scan;template_opposite;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
263
  scan;template_opposite;EleutherAI/pile;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
264
  scan;template_opposite;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;2
265
-
266
- scan;template_right;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
267
- scan;template_right;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
268
  scan;template_right;EleutherAI/pile;corpus;;;0.11;data-based;https://arxiv.org/abs/2310.20707;2
269
  scan;template_right;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;2
270
-
271
  allenai/scicite;;allenai/c4;corpus;;;1.78;data-based;https://arxiv.org/abs/2310.20707;2
272
  allenai/scicite;;oscar-corpus/OSCAR-2301;corpus;;;1.51;data-based;https://arxiv.org/abs/2310.20707;2
273
  allenai/scicite;;EleutherAI/pile;corpus;;;0.86;data-based;https://arxiv.org/abs/2310.20707;2
274
  allenai/scicite;;togethercomputer/RedPajama-Data-V2;corpus;;;1.72;data-based;https://arxiv.org/abs/2310.20707;2
275
-
276
  scitail;snli_format;allenai/c4;corpus;;;0.09;data-based;https://arxiv.org/abs/2310.20707;2
277
  scitail;snli_format;oscar-corpus/OSCAR-2301;corpus;;;0.38;data-based;https://arxiv.org/abs/2310.20707;2
278
  scitail;snli_format;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
279
  scitail;snli_format;togethercomputer/RedPajama-Data-V2;corpus;;;0.71;data-based;https://arxiv.org/abs/2310.20707;2
280
-
281
  scitail;tsv_format;allenai/c4;corpus;;;0.09;data-based;https://arxiv.org/abs/2310.20707;2
282
  scitail;tsv_format;oscar-corpus/OSCAR-2301;corpus;;;0.38;data-based;https://arxiv.org/abs/2310.20707;2
283
  scitail;tsv_format;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
284
  scitail;tsv_format;togethercomputer/RedPajama-Data-V2;corpus;;;0.71;data-based;https://arxiv.org/abs/2310.20707;2
285
-
286
  sem_eval_2014_task_1;;allenai/c4;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;2
287
  sem_eval_2014_task_1;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
288
  sem_eval_2014_task_1;;EleutherAI/pile;corpus;;;4.89;data-based;https://arxiv.org/abs/2310.20707;2
289
  sem_eval_2014_task_1;;togethercomputer/RedPajama-Data-V2;corpus;;;52.81;data-based;https://arxiv.org/abs/2310.20707;2
290
-
291
  sick;;allenai/c4;corpus;;;0.31;data-based;https://arxiv.org/abs/2310.20707;2
292
  sick;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
293
  sick;;EleutherAI/pile;corpus;;;4.79;data-based;https://arxiv.org/abs/2310.20707;2
294
  sick;;togethercomputer/RedPajama-Data-V2;corpus;;;52.61;data-based;https://arxiv.org/abs/2310.20707;2
295
-
296
  snli;;allenai/c4;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
297
  snli;;oscar-corpus/OSCAR-2301;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;2
298
  snli;;EleutherAI/pile;corpus;;;1.11;data-based;https://arxiv.org/abs/2310.20707;2
299
  snli;;togethercomputer/RedPajama-Data-V2;corpus;;;1.22;data-based;https://arxiv.org/abs/2310.20707;2
300
-
301
- squadshifts;amazon;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
302
- squadshifts;amazon;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
303
- squadshifts;amazon;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
304
- squadshifts;amazon;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
305
-
306
  squadshifts;new_wiki;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
307
  squadshifts;new_wiki;oscar-corpus/OSCAR-2301;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
308
  squadshifts;new_wiki;EleutherAI/pile;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
309
  squadshifts;new_wiki;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
310
-
311
  squadshifts;nyt;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
312
  squadshifts;nyt;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
313
  squadshifts;nyt;EleutherAI/pile;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
314
  squadshifts;nyt;togethercomputer/RedPajama-Data-V2;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
315
-
316
  stsb_multi_mt;;allenai/c4;corpus;;;3.48;data-based;https://arxiv.org/abs/2310.20707;2
317
  stsb_multi_mt;;oscar-corpus/OSCAR-2301;corpus;;;3.12;data-based;https://arxiv.org/abs/2310.20707;2
318
  stsb_multi_mt;;EleutherAI/pile;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;2
319
  stsb_multi_mt;;togethercomputer/RedPajama-Data-V2;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;2
320
-
321
- subjqa;books;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
322
- subjqa;books;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
323
- subjqa;books;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
324
- subjqa;books;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
325
-
326
- subjqa;grocery;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
327
- subjqa;grocery;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
328
- subjqa;grocery;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
329
- subjqa;grocery;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
330
-
331
- subjqa;movies;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
332
- subjqa;movies;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
333
- subjqa;movies;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
334
- subjqa;movies;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
335
-
336
- subjqa;restaurants;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
337
- subjqa;restaurants;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
338
- subjqa;restaurants;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
339
- subjqa;restaurants;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
340
-
341
  super_glue;axb;allenai/c4;corpus;;;1.99;data-based;https://arxiv.org/abs/2310.20707;2
342
  super_glue;axb;oscar-corpus/OSCAR-2301;corpus;;;1.45;data-based;https://arxiv.org/abs/2310.20707;2
343
  super_glue;axb;EleutherAI/pile;corpus;;;5.07;data-based;https://arxiv.org/abs/2310.20707;2
344
  super_glue;axb;togethercomputer/RedPajama-Data-V2;corpus;;;6.16;data-based;https://arxiv.org/abs/2310.20707;2
345
-
346
- super_glue;axg;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
347
- super_glue;axg;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
348
  super_glue;axg;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
349
- super_glue;axg;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
350
-
351
- super_glue;boolq;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
352
  super_glue;boolq;oscar-corpus/OSCAR-2301;corpus;;;3.05;data-based;https://arxiv.org/abs/2310.20707;2
353
- super_glue;boolq;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
354
  super_glue;boolq;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
355
-
356
- super_glue;cb;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
357
- super_glue;cb;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
358
- super_glue;cb;EleutherAI/pile;corpus;;;2.0;data-based;https://arxiv.org/abs/2310.20707;2
359
  super_glue;cb;togethercomputer/RedPajama-Data-V2;corpus;;;1.6;data-based;https://arxiv.org/abs/2310.20707;2
360
-
361
  super_glue;copa;allenai/c4;corpus;;;0.6;data-based;https://arxiv.org/abs/2310.20707;2
362
- super_glue;copa;oscar-corpus/OSCAR-2301;corpus;;;1.0;data-based;https://arxiv.org/abs/2310.20707;2
363
  super_glue;copa;EleutherAI/pile;corpus;;;1.2;data-based;https://arxiv.org/abs/2310.20707;2
364
- super_glue;copa;togethercomputer/RedPajama-Data-V2;corpus;;;100.0;data-based;https://arxiv.org/abs/2310.20707;2
365
-
366
- super_glue;multirc;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
367
- super_glue;multirc;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
368
- super_glue;multirc;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
369
- super_glue;multirc;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
370
-
371
- super_glue;record;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
372
- super_glue;record;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
373
- super_glue;record;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
374
- super_glue;record;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
375
-
376
  super_glue;rte;allenai/c4;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
377
  super_glue;rte;oscar-corpus/OSCAR-2301;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;2
378
  super_glue;rte;EleutherAI/pile;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
379
  super_glue;rte;togethercomputer/RedPajama-Data-V2;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;2
380
-
381
  super_glue;wic;allenai/c4;corpus;;;64.43;data-based;https://arxiv.org/abs/2310.20707;2
382
  super_glue;wic;oscar-corpus/OSCAR-2301;corpus;;;49.43;data-based;https://arxiv.org/abs/2310.20707;2
383
  super_glue;wic;EleutherAI/pile;corpus;;;18.57;data-based;https://arxiv.org/abs/2310.20707;2
384
  super_glue;wic;togethercomputer/RedPajama-Data-V2;corpus;;;60.21;data-based;https://arxiv.org/abs/2310.20707;2
385
-
386
  swag;regular;allenai/c4;corpus;;;2.48;data-based;https://arxiv.org/abs/2310.20707;2
387
  swag;regular;oscar-corpus/OSCAR-2301;corpus;;;1.65;data-based;https://arxiv.org/abs/2310.20707;2
388
  swag;regular;EleutherAI/pile;corpus;;;2.21;data-based;https://arxiv.org/abs/2310.20707;2
389
  swag;regular;togethercomputer/RedPajama-Data-V2;corpus;;;2.79;data-based;https://arxiv.org/abs/2310.20707;2
390
-
391
- tab_fact;tab_fact;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
392
- tab_fact;tab_fact;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
393
- tab_fact;tab_fact;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
394
- tab_fact;tab_fact;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
395
-
396
  wiki_qa;;allenai/c4;corpus;;;0.24;data-based;https://arxiv.org/abs/2310.20707;2
397
  wiki_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
398
  wiki_qa;;EleutherAI/pile;corpus;;;0.19;data-based;https://arxiv.org/abs/2310.20707;2
399
  wiki_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.91;data-based;https://arxiv.org/abs/2310.20707;2
400
-
401
- winograd_wsc;wsc273;allenai/c4;corpus;;;29.30;data-based;https://arxiv.org/abs/2310.20707;2
402
- winograd_wsc;wsc273;oscar-corpus/OSCAR-2301;corpus;;;30.40;data-based;https://arxiv.org/abs/2310.20707;2
403
  winograd_wsc;wsc273;EleutherAI/pile;corpus;;;32.23;data-based;https://arxiv.org/abs/2310.20707;2
404
  winograd_wsc;wsc273;togethercomputer/RedPajama-Data-V2;corpus;;;58.24;data-based;https://arxiv.org/abs/2310.20707;2
405
-
406
- winogrande;winogrande_xl;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
407
- winogrande;winogrande_xl;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
408
- winogrande;winogrande_xl;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
409
- winogrande;winogrande_xl;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
410
-
411
  xnli;en;allenai/c4;corpus;;;0.12;data-based;https://arxiv.org/abs/2310.20707;2
412
  xnli;en;oscar-corpus/OSCAR-2301;corpus;;;0.24;data-based;https://arxiv.org/abs/2310.20707;2
413
  xnli;en;EleutherAI/pile;corpus;;;0.36;data-based;https://arxiv.org/abs/2310.20707;2
414
  xnli;en;togethercomputer/RedPajama-Data-V2;corpus;;;0.44;data-based;https://arxiv.org/abs/2310.20707;2
415
-
416
  xsum;;allenai/c4;corpus;;;2.13;data-based;https://arxiv.org/abs/2310.20707;2
417
  xsum;;oscar-corpus/OSCAR-2301;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
418
- xsum;;EleutherAI/pile;corpus;;;3.30;data-based;https://arxiv.org/abs/2310.20707;2
419
  xsum;;togethercomputer/RedPajama-Data-V2;corpus;;;4.28;data-based;https://arxiv.org/abs/2310.20707;2
420
-
421
- zest;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
422
- zest;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
423
- zest;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
424
- zest;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
425
-
426
-
427
- imdb;;GPT-4;model;100.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
428
- imdb;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
429
-
430
- ag_news;;GPT-4;model;100.0;;100.0;model-based;https://arxiv.org/pdf/2308.08493;3
431
- ag_news;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
432
-
433
- yelp_review_full;;GPT-4;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
434
- yelp_review_full;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
435
-
436
- nyu-mll/glue;rte;GPT-4;model;100.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
437
- nyu-mll/glue;rte;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
438
-
439
- nyu-mll/glue;wnli;GPT-4;model;100.0;;100.0;model-based;https://arxiv.org/pdf/2308.08493;3
440
- nyu-mll/glue;wnli;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
441
-
442
- samsum;;GPT-4;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
443
- samsum;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
444
-
445
- EdinburghNLP/xsum;;GPT-4;model;0.0;;100.0;model-based;https://arxiv.org/pdf/2308.08493;3
446
- EdinburghNLP/xsum;;GPT-3.5;model;0.0;;100.0;model-based;https://arxiv.org/pdf/2308.08493;3
 
 
1
  Evaluation Dataset;Subset;Contaminated Source;Model or corpus;Train Split;Development Split;Test Split;Approach;Reference;PR
2
+ conll2003;;GPT-3.5;Model;100;100;100;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
3
+ nyu-mll/glue;mnli;GPT-3.5;Model;100;100;100;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
4
+ rajpurkar/squad_v2;;GPT-3.5;Model;100;100;0;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
5
+ https://catalog.ldc.upenn.edu/LDC2006T06;;GPT-3.5;Model;100;100;100;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
6
+ quac;;GPT-3.5;Model;100;100;0;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
7
+ natural_questions;;GPT-3.5;Model;100;100;0;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
8
+ google/boolq;;GPT-3.5;Model;100;100;0;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
9
+
10
  lama;T-REx;allenai/c4;corpus;;;4.6;data-based;https://arxiv.org/abs/2104.08758;6
11
  lama;Google-RE;allenai/c4;corpus;;;5.7;data-based;https://arxiv.org/abs/2104.08758;6
12
  EdinburghNLP/xsum;;allenai/c4;corpus;;;15.49;data-based;https://arxiv.org/abs/2104.08758;6
 
22
  nyu-mll/glue;MRPC-sentence-2;allenai/c4;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
23
  nyu-mll/glue;QNLI-sentence;allenai/c4;corpus;;;53.6;data-based;https://arxiv.org/abs/2104.08758;6
24
  nyu-mll/glue;QNLI-question;allenai/c4;corpus;;;1.8;data-based;https://arxiv.org/abs/2104.08758;6
25
+ nyu-mll/glue;RTE-sentence-1;allenai/c4;corpus;;;6;data-based;https://arxiv.org/abs/2104.08758;6
26
  nyu-mll/glue;RTE-sentence-2;allenai/c4;corpus;;;10.8;data-based;https://arxiv.org/abs/2104.08758;6
27
+ nyu-mll/glue;SST-2;allenai/c4;corpus;;;11;data-based;https://arxiv.org/abs/2104.08758;6
28
  nyu-mll/glue;STS-B-sentence-1;allenai/c4;corpus;;;18.3;data-based;https://arxiv.org/abs/2104.08758;6
29
  nyu-mll/glue;STS-B-sentence-2;allenai/c4;corpus;;;18.6;data-based;https://arxiv.org/abs/2104.08758;6
30
  nyu-mll/glue;WNLI-sentence-1;allenai/c4;corpus;;;4.8;data-based;https://arxiv.org/abs/2104.08758;6
 
35
  UCLNLP/adversarial_qa;adversarialQA;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
36
  UCLNLP/adversarial_qa;adversarialQA;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
37
 
38
+ UCLNLP/adversarial_qa;dbert;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
39
+ UCLNLP/adversarial_qa;dbert;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
40
+ UCLNLP/adversarial_qa;dbert;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
41
+ UCLNLP/adversarial_qa;dbert;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
42
 
43
+ UCLNLP/adversarial_qa;dbidaf;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
44
+ UCLNLP/adversarial_qa;dbidaf;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
45
+ UCLNLP/adversarial_qa;dbidaf;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
46
+ UCLNLP/adversarial_qa;dbidaf;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
47
 
48
  UCLNLP/adversarial_qa;droberta;allenai/c4;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
49
  UCLNLP/adversarial_qa;droberta;oscar-corpus/OSCAR-2301;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
50
  UCLNLP/adversarial_qa;droberta;EleutherAI/pile;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
51
+ UCLNLP/adversarial_qa;droberta;togethercomputer/RedPajama-Data-V2;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;
52
 
53
  aeslc;;allenai/c4;corpus;;;1.57;data-based;https://arxiv.org/abs/2310.20707;2
54
  aeslc;;oscar-corpus/OSCAR-2301;corpus;;;0.31;data-based;https://arxiv.org/abs/2310.20707;2
 
56
  aeslc;;togethercomputer/RedPajama-Data-V2;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
57
 
58
  amazon_reviews_multi;;allenai/c4;corpus;;;2.28;data-based;https://arxiv.org/abs/2310.20707;2
59
+ amazon_reviews_multi;;oscar-corpus/OSCAR-2301;corpus;;;2.1;data-based;https://arxiv.org/abs/2310.20707;2
60
  amazon_reviews_multi;;EleutherAI/pile;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;2
61
  amazon_reviews_multi;;togethercomputer/RedPajama-Data-V2;corpus;;;2.06;data-based;https://arxiv.org/abs/2310.20707;2
62
 
 
65
  billsum;;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
66
  billsum;;togethercomputer/RedPajama-Data-V2;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
67
 
68
+ cosmos_qa;;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
69
+ cosmos_qa;;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
70
+ cosmos_qa;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
71
+ cosmos_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
72
 
73
+ crows_pairs;;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
74
  crows_pairs;;oscar-corpus/OSCAR-2301;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
75
+ crows_pairs;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
76
+ crows_pairs;;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
77
 
78
+ ibm/duorc;ParaphraseRC;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
79
+ ibm/duorc;ParaphraseRC;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
80
+ ibm/duorc;ParaphraseRC;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
81
+ ibm/duorc;ParaphraseRC;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
82
 
83
  ibm/duorc;SelfRC;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
84
+ ibm/duorc;SelfRC;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
85
  ibm/duorc;SelfRC;EleutherAI/pile;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
86
  ibm/duorc;SelfRC;togethercomputer/RedPajama-Data-V2;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
87
 
 
111
  nyu-mll/glue;mnli-mismatched;togethercomputer/RedPajama-Data-V2;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;2
112
 
113
  nyu-mll/glue;mrpc;allenai/c4;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
114
+ nyu-mll/glue;mrpc;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
115
  nyu-mll/glue;mrpc;EleutherAI/pile;corpus;;;0.64;data-based;https://arxiv.org/abs/2310.20707;2
116
  nyu-mll/glue;mrpc;togethercomputer/RedPajama-Data-V2;corpus;;;1.16;data-based;https://arxiv.org/abs/2310.20707;2
117
 
 
120
  nyu-mll/glue;qnli;EleutherAI/pile;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;2
121
  nyu-mll/glue;qnli;togethercomputer/RedPajama-Data-V2;corpus;;;1.21;data-based;https://arxiv.org/abs/2310.20707;2
122
 
123
+ nyu-mll/glue;rte;allenai/c4;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
124
  nyu-mll/glue;rte;oscar-corpus/OSCAR-2301;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;2
125
  nyu-mll/glue;rte;EleutherAI/pile;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
126
  nyu-mll/glue;rte;togethercomputer/RedPajama-Data-V2;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;2
 
130
  nyu-mll/glue;stsb;EleutherAI/pile;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;2
131
  nyu-mll/glue;stsb;togethercomputer/RedPajama-Data-V2;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;2
132
 
133
+ nyu-mll/glue;wnli;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
134
+ nyu-mll/glue;wnli;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
135
+ nyu-mll/glue;wnli;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
136
  nyu-mll/glue;wnli;togethercomputer/RedPajama-Data-V2;corpus;;;2.05;data-based;https://arxiv.org/abs/2310.20707;2
137
 
138
  head_qa;en;allenai/c4;corpus;;;5.22;data-based;https://arxiv.org/abs/2310.20707;2
 
141
  head_qa;en;togethercomputer/RedPajama-Data-V2;corpus;;;5.94;data-based;https://arxiv.org/abs/2310.20707;2
142
 
143
  health_fact;;allenai/c4;corpus;;;7.53;data-based;https://arxiv.org/abs/2310.20707;2
144
+ health_fact;;oscar-corpus/OSCAR-2301;corpus;;;3.4;data-based;https://arxiv.org/abs/2310.20707;2
145
  health_fact;;EleutherAI/pile;corpus;;;1.94;data-based;https://arxiv.org/abs/2310.20707;2
146
+ health_fact;;togethercomputer/RedPajama-Data-V2;corpus;;;18.7;data-based;https://arxiv.org/abs/2310.20707;2
147
 
148
+ hlgd;;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
149
+ hlgd;;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
150
+ hlgd;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
151
+ hlgd;;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
152
 
153
  liar;;allenai/c4;corpus;;;29.23;data-based;https://arxiv.org/abs/2310.20707;2
154
  liar;;oscar-corpus/OSCAR-2301;corpus;;;13.95;data-based;https://arxiv.org/abs/2310.20707;2
155
  liar;;EleutherAI/pile;corpus;;;10.91;data-based;https://arxiv.org/abs/2310.20707;2
156
  liar;;togethercomputer/RedPajama-Data-V2;corpus;;;45.05;data-based;https://arxiv.org/abs/2310.20707;2
157
 
158
+ math_dataset;algebra__linear_1d;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
159
+ math_dataset;algebra__linear_1d;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
160
+ math_dataset;algebra__linear_1d;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
161
+ math_dataset;algebra__linear_1d;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
162
 
163
+ math_dataset;algebra__linear_2d;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
164
+ math_dataset;algebra__linear_2d;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
165
+ math_dataset;algebra__linear_2d;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
166
+ math_dataset;algebra__linear_2d;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
167
 
168
+ math_dataset;algebra__linear_2d_composed;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
169
+ math_dataset;algebra__linear_2d_composed;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
170
+ math_dataset;algebra__linear_2d_composed;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
171
+ math_dataset;algebra__linear_2d_composed;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
172
 
173
  math_qa;;allenai/c4;corpus;;;0.34;data-based;https://arxiv.org/abs/2310.20707;2
174
  math_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
175
+ math_qa;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
176
  math_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.07;data-based;https://arxiv.org/abs/2310.20707;2
177
 
178
+ mc_taco;;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
179
+ mc_taco;;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
180
+ mc_taco;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
181
  mc_taco;;togethercomputer/RedPajama-Data-V2;corpus;;;0.14;data-based;https://arxiv.org/abs/2310.20707;2
182
 
183
+ mocha;;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
184
+ mocha;;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
185
+ mocha;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
186
+ mocha;;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
187
 
188
+ openai_humaneval;;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
189
  openai_humaneval;;oscar-corpus/OSCAR-2301;corpus;;;1.22;data-based;https://arxiv.org/abs/2310.20707;2
190
+ openai_humaneval;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
191
+ openai_humaneval;;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
192
 
193
  paws-x;en;allenai/c4;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;2
194
+ paws-x;en;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
195
  paws-x;en;EleutherAI/pile;corpus;;;0.15;data-based;https://arxiv.org/abs/2310.20707;2
196
  paws-x;en;togethercomputer/RedPajama-Data-V2;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
197
 
 
207
 
208
  race;all;allenai/c4;corpus;;;0.14;data-based;https://arxiv.org/abs/2310.20707;2
209
  race;all;oscar-corpus/OSCAR-2301;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
210
+ race;all;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
211
  race;all;togethercomputer/RedPajama-Data-V2;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
212
 
213
  race;high;allenai/c4;corpus;;;0.11;data-based;https://arxiv.org/abs/2310.20707;2
214
+ race;high;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
215
+ race;high;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
216
  race;high;togethercomputer/RedPajama-Data-V2;corpus;;;0.26;data-based;https://arxiv.org/abs/2310.20707;2
217
 
218
  race;middle;allenai/c4;corpus;;;0.21;data-based;https://arxiv.org/abs/2310.20707;2
219
  race;middle;oscar-corpus/OSCAR-2301;corpus;;;0.21;data-based;https://arxiv.org/abs/2310.20707;2
220
+ race;middle;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
221
  race;middle;togethercomputer/RedPajama-Data-V2;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;2
222
 
223
+ allenai/ropes;;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
224
+ allenai/ropes;;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
225
+ allenai/ropes;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
226
+ allenai/ropes;;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
227
 
228
+ samsum;;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
229
+ samsum;;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
230
+ samsum;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
231
  samsum;;togethercomputer/RedPajama-Data-V2;corpus;;;0.12;data-based;https://arxiv.org/abs/2310.20707;2
232
 
233
+ scan;addprim_jump;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
234
+ scan;addprim_jump;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
235
  scan;addprim_jump;EleutherAI/pile;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;2
236
  scan;addprim_jump;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;2
237
 
238
+ scan;addprim_turn;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
239
+ scan;addprim_turn;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
240
  scan;addprim_turn;EleutherAI/pile;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;2
241
+ scan;addprim_turn;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
242
+
243
+ scan;filler_num0;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
244
+ scan;filler_num0;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
245
+ scan;filler_num0;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
246
  scan;filler_num0;togethercomputer/RedPajama-Data-V2;corpus;;;0.9;data-based;https://arxiv.org/abs/2310.20707;2
247
+
248
+ scan;length;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
249
+ scan;length;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
250
  scan;length;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
251
+ scan;length;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
252
+
253
  scan;simple;allenai/c4;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
254
+ scan;simple;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
255
  scan;simple;EleutherAI/pile;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
256
  scan;simple;togethercomputer/RedPajama-Data-V2;corpus;;;0.26;data-based;https://arxiv.org/abs/2310.20707;2
257
+
258
+ scan;template_around;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
259
+ scan;template_around;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
260
+ scan;template_around;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
261
  scan;template_around;togethercomputer/RedPajama-Data-V2;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
262
+
263
+ scan;template_jump;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
264
+ scan;template_jump;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
265
+ scan;template_jump;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
266
  scan;template_jump;togethercomputer/RedPajama-Data-V2;corpus;;;0.9;data-based;https://arxiv.org/abs/2310.20707;2
267
+
268
+ scan;template_opposite;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
269
+ scan;template_opposite;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
270
  scan;template_opposite;EleutherAI/pile;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
271
  scan;template_opposite;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;2
272
+
273
+ scan;template_right;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
274
+ scan;template_right;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
275
  scan;template_right;EleutherAI/pile;corpus;;;0.11;data-based;https://arxiv.org/abs/2310.20707;2
276
  scan;template_right;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;2
277
+
278
  allenai/scicite;;allenai/c4;corpus;;;1.78;data-based;https://arxiv.org/abs/2310.20707;2
279
  allenai/scicite;;oscar-corpus/OSCAR-2301;corpus;;;1.51;data-based;https://arxiv.org/abs/2310.20707;2
280
  allenai/scicite;;EleutherAI/pile;corpus;;;0.86;data-based;https://arxiv.org/abs/2310.20707;2
281
  allenai/scicite;;togethercomputer/RedPajama-Data-V2;corpus;;;1.72;data-based;https://arxiv.org/abs/2310.20707;2
282
+
283
  scitail;snli_format;allenai/c4;corpus;;;0.09;data-based;https://arxiv.org/abs/2310.20707;2
284
  scitail;snli_format;oscar-corpus/OSCAR-2301;corpus;;;0.38;data-based;https://arxiv.org/abs/2310.20707;2
285
  scitail;snli_format;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
286
  scitail;snli_format;togethercomputer/RedPajama-Data-V2;corpus;;;0.71;data-based;https://arxiv.org/abs/2310.20707;2
287
+
288
  scitail;tsv_format;allenai/c4;corpus;;;0.09;data-based;https://arxiv.org/abs/2310.20707;2
289
  scitail;tsv_format;oscar-corpus/OSCAR-2301;corpus;;;0.38;data-based;https://arxiv.org/abs/2310.20707;2
290
  scitail;tsv_format;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
291
  scitail;tsv_format;togethercomputer/RedPajama-Data-V2;corpus;;;0.71;data-based;https://arxiv.org/abs/2310.20707;2
292
+
293
  sem_eval_2014_task_1;;allenai/c4;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;2
294
  sem_eval_2014_task_1;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
295
  sem_eval_2014_task_1;;EleutherAI/pile;corpus;;;4.89;data-based;https://arxiv.org/abs/2310.20707;2
296
  sem_eval_2014_task_1;;togethercomputer/RedPajama-Data-V2;corpus;;;52.81;data-based;https://arxiv.org/abs/2310.20707;2
297
+
298
  sick;;allenai/c4;corpus;;;0.31;data-based;https://arxiv.org/abs/2310.20707;2
299
  sick;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
300
  sick;;EleutherAI/pile;corpus;;;4.79;data-based;https://arxiv.org/abs/2310.20707;2
301
  sick;;togethercomputer/RedPajama-Data-V2;corpus;;;52.61;data-based;https://arxiv.org/abs/2310.20707;2
302
+
303
  snli;;allenai/c4;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
304
  snli;;oscar-corpus/OSCAR-2301;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;2
305
  snli;;EleutherAI/pile;corpus;;;1.11;data-based;https://arxiv.org/abs/2310.20707;2
306
  snli;;togethercomputer/RedPajama-Data-V2;corpus;;;1.22;data-based;https://arxiv.org/abs/2310.20707;2
307
+
308
+ squadshifts;amazon;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
309
+ squadshifts;amazon;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
310
+ squadshifts;amazon;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
311
+ squadshifts;amazon;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
312
+
313
  squadshifts;new_wiki;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
314
  squadshifts;new_wiki;oscar-corpus/OSCAR-2301;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
315
  squadshifts;new_wiki;EleutherAI/pile;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
316
  squadshifts;new_wiki;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
317
+
318
  squadshifts;nyt;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
319
  squadshifts;nyt;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
320
  squadshifts;nyt;EleutherAI/pile;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
321
  squadshifts;nyt;togethercomputer/RedPajama-Data-V2;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
322
+
323
  stsb_multi_mt;;allenai/c4;corpus;;;3.48;data-based;https://arxiv.org/abs/2310.20707;2
324
  stsb_multi_mt;;oscar-corpus/OSCAR-2301;corpus;;;3.12;data-based;https://arxiv.org/abs/2310.20707;2
325
  stsb_multi_mt;;EleutherAI/pile;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;2
326
  stsb_multi_mt;;togethercomputer/RedPajama-Data-V2;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;2
327
+
328
+ subjqa;books;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
329
+ subjqa;books;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
330
+ subjqa;books;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
331
+ subjqa;books;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
332
+
333
+ subjqa;grocery;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
334
+ subjqa;grocery;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
335
+ subjqa;grocery;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
336
+ subjqa;grocery;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
337
+
338
+ subjqa;movies;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
339
+ subjqa;movies;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
340
+ subjqa;movies;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
341
+ subjqa;movies;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
342
+
343
+ subjqa;restaurants;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
344
+ subjqa;restaurants;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
345
+ subjqa;restaurants;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
346
+ subjqa;restaurants;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
347
+
348
  super_glue;axb;allenai/c4;corpus;;;1.99;data-based;https://arxiv.org/abs/2310.20707;2
349
  super_glue;axb;oscar-corpus/OSCAR-2301;corpus;;;1.45;data-based;https://arxiv.org/abs/2310.20707;2
350
  super_glue;axb;EleutherAI/pile;corpus;;;5.07;data-based;https://arxiv.org/abs/2310.20707;2
351
  super_glue;axb;togethercomputer/RedPajama-Data-V2;corpus;;;6.16;data-based;https://arxiv.org/abs/2310.20707;2
352
+
353
+ super_glue;axg;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
354
+ super_glue;axg;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
355
  super_glue;axg;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
356
+ super_glue;axg;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
357
+
358
+ super_glue;boolq;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
359
  super_glue;boolq;oscar-corpus/OSCAR-2301;corpus;;;3.05;data-based;https://arxiv.org/abs/2310.20707;2
360
+ super_glue;boolq;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
361
  super_glue;boolq;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
362
+
363
+ super_glue;cb;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
364
+ super_glue;cb;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
365
+ super_glue;cb;EleutherAI/pile;corpus;;;2;data-based;https://arxiv.org/abs/2310.20707;2
366
  super_glue;cb;togethercomputer/RedPajama-Data-V2;corpus;;;1.6;data-based;https://arxiv.org/abs/2310.20707;2
367
+
368
  super_glue;copa;allenai/c4;corpus;;;0.6;data-based;https://arxiv.org/abs/2310.20707;2
369
+ super_glue;copa;oscar-corpus/OSCAR-2301;corpus;;;1;data-based;https://arxiv.org/abs/2310.20707;2
370
  super_glue;copa;EleutherAI/pile;corpus;;;1.2;data-based;https://arxiv.org/abs/2310.20707;2
371
+ super_glue;copa;togethercomputer/RedPajama-Data-V2;corpus;;;100;data-based;https://arxiv.org/abs/2310.20707;2
372
+
373
+ super_glue;multirc;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
374
+ super_glue;multirc;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
375
+ super_glue;multirc;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
376
+ super_glue;multirc;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
377
+
378
+ super_glue;record;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
379
+ super_glue;record;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
380
+ super_glue;record;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
381
+ super_glue;record;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
382
+
383
  super_glue;rte;allenai/c4;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
384
  super_glue;rte;oscar-corpus/OSCAR-2301;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;2
385
  super_glue;rte;EleutherAI/pile;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
386
  super_glue;rte;togethercomputer/RedPajama-Data-V2;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;2
387
+
388
  super_glue;wic;allenai/c4;corpus;;;64.43;data-based;https://arxiv.org/abs/2310.20707;2
389
  super_glue;wic;oscar-corpus/OSCAR-2301;corpus;;;49.43;data-based;https://arxiv.org/abs/2310.20707;2
390
  super_glue;wic;EleutherAI/pile;corpus;;;18.57;data-based;https://arxiv.org/abs/2310.20707;2
391
  super_glue;wic;togethercomputer/RedPajama-Data-V2;corpus;;;60.21;data-based;https://arxiv.org/abs/2310.20707;2
392
+
393
  swag;regular;allenai/c4;corpus;;;2.48;data-based;https://arxiv.org/abs/2310.20707;2
394
  swag;regular;oscar-corpus/OSCAR-2301;corpus;;;1.65;data-based;https://arxiv.org/abs/2310.20707;2
395
  swag;regular;EleutherAI/pile;corpus;;;2.21;data-based;https://arxiv.org/abs/2310.20707;2
396
  swag;regular;togethercomputer/RedPajama-Data-V2;corpus;;;2.79;data-based;https://arxiv.org/abs/2310.20707;2
397
+
398
+ tab_fact;tab_fact;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
399
+ tab_fact;tab_fact;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
400
+ tab_fact;tab_fact;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
401
+ tab_fact;tab_fact;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
402
+
403
  wiki_qa;;allenai/c4;corpus;;;0.24;data-based;https://arxiv.org/abs/2310.20707;2
404
  wiki_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
405
  wiki_qa;;EleutherAI/pile;corpus;;;0.19;data-based;https://arxiv.org/abs/2310.20707;2
406
  wiki_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.91;data-based;https://arxiv.org/abs/2310.20707;2
407
+
408
+ winograd_wsc;wsc273;allenai/c4;corpus;;;29.3;data-based;https://arxiv.org/abs/2310.20707;2
409
+ winograd_wsc;wsc273;oscar-corpus/OSCAR-2301;corpus;;;30.4;data-based;https://arxiv.org/abs/2310.20707;2
410
  winograd_wsc;wsc273;EleutherAI/pile;corpus;;;32.23;data-based;https://arxiv.org/abs/2310.20707;2
411
  winograd_wsc;wsc273;togethercomputer/RedPajama-Data-V2;corpus;;;58.24;data-based;https://arxiv.org/abs/2310.20707;2
412
+
413
+ winogrande;winogrande_xl;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
414
+ winogrande;winogrande_xl;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
415
+ winogrande;winogrande_xl;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
416
+ winogrande;winogrande_xl;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
417
+
418
  xnli;en;allenai/c4;corpus;;;0.12;data-based;https://arxiv.org/abs/2310.20707;2
419
  xnli;en;oscar-corpus/OSCAR-2301;corpus;;;0.24;data-based;https://arxiv.org/abs/2310.20707;2
420
  xnli;en;EleutherAI/pile;corpus;;;0.36;data-based;https://arxiv.org/abs/2310.20707;2
421
  xnli;en;togethercomputer/RedPajama-Data-V2;corpus;;;0.44;data-based;https://arxiv.org/abs/2310.20707;2
422
+
423
  xsum;;allenai/c4;corpus;;;2.13;data-based;https://arxiv.org/abs/2310.20707;2
424
  xsum;;oscar-corpus/OSCAR-2301;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
425
+ xsum;;EleutherAI/pile;corpus;;;3.3;data-based;https://arxiv.org/abs/2310.20707;2
426
  xsum;;togethercomputer/RedPajama-Data-V2;corpus;;;4.28;data-based;https://arxiv.org/abs/2310.20707;2
427
+
428
+ zest;;allenai/c4;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
429
+ zest;;oscar-corpus/OSCAR-2301;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
430
+ zest;;EleutherAI/pile;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
431
+ zest;;togethercomputer/RedPajama-Data-V2;corpus;;;0;data-based;https://arxiv.org/abs/2310.20707;2
432
+
433
+
434
+ imdb;;GPT-4;model;100;;0;model-based;https://arxiv.org/pdf/2308.08493;3
435
+ imdb;;GPT-3.5;model;0;;0;model-based;https://arxiv.org/pdf/2308.08493;3
436
+
437
+ ag_news;;GPT-4;model;100;;100;model-based;https://arxiv.org/pdf/2308.08493;3
438
+ ag_news;;GPT-3.5;model;0;;0;model-based;https://arxiv.org/pdf/2308.08493;3
439
+
440
+ yelp_review_full;;GPT-4;model;0;;0;model-based;https://arxiv.org/pdf/2308.08493;3
441
+ yelp_review_full;;GPT-3.5;model;0;;0;model-based;https://arxiv.org/pdf/2308.08493;3
442
+
443
+ nyu-mll/glue;rte;GPT-4;model;100;;0;model-based;https://arxiv.org/pdf/2308.08493;3
444
+ nyu-mll/glue;rte;GPT-3.5;model;0;;0;model-based;https://arxiv.org/pdf/2308.08493;3
445
+
446
+ nyu-mll/glue;wnli;GPT-4;model;100;;100;model-based;https://arxiv.org/pdf/2308.08493;3
447
+ nyu-mll/glue;wnli;GPT-3.5;model;0;;0;model-based;https://arxiv.org/pdf/2308.08493;3
448
+
449
+ samsum;;GPT-4;model;0;;0;model-based;https://arxiv.org/pdf/2308.08493;3
450
+ samsum;;GPT-3.5;model;0;;0;model-based;https://arxiv.org/pdf/2308.08493;3
451
+
452
+ EdinburghNLP/xsum;;GPT-4;model;0;;100;model-based;https://arxiv.org/pdf/2308.08493;3
453
+ EdinburghNLP/xsum;;GPT-3.5;model;0;;100;model-based;https://arxiv.org/pdf/2308.08493;3
454
+