File size: 4,548 Bytes
efeee6d
314f91a
95f85ed
b2202ce
efeee6d
 
 
 
 
 
314f91a
efeee6d
 
943f952
54510cc
a17a7f2
2eb0923
a17a7f2
 
b2202ce
a17a7f2
b2202ce
efeee6d
 
 
8eb0e38
58733e4
efeee6d
9672344
 
 
7e99ffa
0227006
efeee6d
0227006
d313dbd
 
8eb0e38
 
 
 
 
 
 
a17a7f2
 
 
 
 
 
 
 
8eb0e38
7e99ffa
 
d313dbd
8eb0e38
d16cee2
d313dbd
 
8c49cb6
d313dbd
 
 
 
 
 
 
 
 
8c49cb6
b323764
d313dbd
 
 
 
 
 
 
 
b323764
d313dbd
 
 
 
8c49cb6
 
d16cee2
58733e4
2a73469
 
217b585
4b0c310
 
 
 
 
 
9833cdb
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
from dataclasses import dataclass
from enum import Enum


@dataclass
class Task:
    benchmark: str
    metric: str
    col_name: str


# Init: to update with your specific keys
class Tasks(Enum):
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
    task0 = Task("toxicity", "aggregated-results", "Non-toxicity")
    task1 = Task("stereotype", "aggregated-results", "Stereotype")
    task2 = Task("adv", "aggregated-results", "AdvGLUE++")
    task3 = Task("ood", "aggregated-results", "OoD")
    task4 = Task("adv_demo", "aggregated-results", "Adv Demo")
    task5 = Task("privacy", "aggregated-results", "Privacy")
    task6 = Task("ethics", "aggregated-results", "Ethics")
    task7 = Task("fairness", "aggregated-results", "Fairness")


# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">Trustworthy LLM leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """Powered by the DecodingTrust platform, which provides comprehensive safety and trustworthiness 
evaluation for LLMs, this leaderboard is designed to help researchers and practitioners better understand the 
capabilities, limitations, and potential risks of state-of-the-art Large Language Models (LLMs). See our paper for 
details. Access the DecodingTrust platform website [here](https://decodingtrust.github.io/)."""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works

DecodingTrust aims at providing a thorough assessment of trustworthiness in GPT models.

This research endeavor is designed to help researchers and practitioners better understand the capabilities, 
limitations, and potential risks involved in deploying these state-of-the-art Large Language Models (LLMs).

This project is organized around the following eight primary perspectives of trustworthiness, including:

+ Toxicity
+ Stereotype and bias
+ Adversarial robustness
+ Out-of-Distribution Robustness
+ Privacy
+ Robustness to Adversarial Demonstrations
+ Machine Ethics
+ Fairness

We normalize the score of each perspective as 0-100, and these scores are the higher the better.

## Reproducibility
To reproduce our results, checkout https://github.com/AI-secure/DecodingTrust

"""

EVALUATION_QUEUE_TEXT = """
## Some good practices before submitting a model

### 1) Make sure you can load your model and tokenizer using AutoClasses:
```python
from transformers import AutoConfig, AutoModel, AutoTokenizer
config = AutoConfig.from_pretrained("your model name", revision=revision)
model = AutoModel.from_pretrained("your model name", revision=revision)
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
```
If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.

Note: make sure your model is public!
Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!

### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!

### 3) Make sure your model has an open license!
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗

### 4) Fill up your model card
When we add extra information about models to the leaderboard, it will be automatically taken from the model card

## In case of model failure
If your model is displayed in the `FAILED` category, its execution stopped.
Make sure you have followed the above steps first.
If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
@article{wang2023decodingtrust,
  title={DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models},
  author={Wang, Boxin and Chen, Weixin and Pei, Hengzhi and Xie, Chulin and Kang, Mintong and Zhang, Chenhui and Xu, Chejian and Xiong, Zidi and Dutta, Ritik and Schaeffer, Rylan and others},
  booktitle={Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
  year={2023}
}
"""