Update README.md

README.md

@@ -17,141 +17,205 @@ tags:
 - rlhf
 pipeline_tag: zero-shot-classification
 datasets:
-- hellaswag
-- ag_news
-- pietrolesci/nli_fever
-- numer_sense
-- go_emotions
-- Ericwang/promptProficiency
-- poem_sentiment
-- pietrolesci/robust_nli_is_sd
-- sileod/probability_words_nli
-- social_i_qa
-- trec
-- imppres
-- pietrolesci/gen_debiased_nli
-- snips_built_in_intents
-- metaeval/imppres
-- metaeval/crowdflower
-- tals/vitaminc
-- dream
-- metaeval/babi_nli
-- Ericwang/promptSpoke
-- metaeval/ethics
-- art
-- ai2_arc
-- discovery
-- Ericwang/promptGrammar
-- code_x_glue_cc_clone_detection_big_clone_bench
-- prajjwal1/discosense
-- pietrolesci/joci
-- Anthropic/model-written-evals
-- utilitarianism
-- emo
-- tweets_hate_speech_detection
-- piqa
-- blog_authorship_corpus
-- SpeedOfMagic/ontonotes_english
-- circa
-- app_reviews
-- anli
-- Ericwang/promptSentiment
-- codah
-- definite_pronoun_resolution
-- health_fact
-- tweet_eval
-- hate_speech18
 - glue
-- hendrycks_test
-- paws
-- bigbench
-- hate_speech_offensive
-- blimp
+- super_glue
+- anli
+- metaeval/babi_nli
 - sick
-- turingbench/TuringBench
-- martn-nguyen/contrast_nli
-- Anthropic/hh-rlhf
-- openbookqa
-- species_800
+- snli
+- scitail
+- hans
 - alisawuffles/WANLI
-- ethos
+- metaeval/recast
+- sileod/probability_words_nli
+- joey234/nan-nli
+- pietrolesci/nli_fever
+- pietrolesci/breaking_nli
+- pietrolesci/conj_nli
+- pietrolesci/fracas
+- pietrolesci/dialogue_nli
 - pietrolesci/mpe
-- wiki_hop
-- pietrolesci/glue_diagnostics
-- mc_taco
-- quarel
-- PiC/phrase_similarity
-- strombergnlp/rumoureval_2019
-- quail
-- acronym_identification
-- pietrolesci/robust_nli
-- quora
-- wnut_17
-- dynabench/dynasent
+- pietrolesci/dnc
 - pietrolesci/gpt3_nli
-- truthful_qa
+- pietrolesci/recast_white
+- pietrolesci/joci
+- martn-nguyen/contrast_nli
+- pietrolesci/robust_nli
+- pietrolesci/robust_nli_is_sd
+- pietrolesci/robust_nli_li_ts
+- pietrolesci/gen_debiased_nli
 - pietrolesci/add_one_rte
-- pietrolesci/breaking_nli
-- copenlu/scientific-exaggeration-detection
+- metaeval/imppres
+- pietrolesci/glue_diagnostics
+- hlgd
+- paws
+- quora
 - medical_questions_pairs
-- rotten_tomatoes
-- scicite
-- scitail
-- pietrolesci/dialogue_nli
-- code_x_glue_cc_defect_detection
+- conll2003
+- Anthropic/hh-rlhf
+- Anthropic/model-written-evals
+- truthful_qa
 - nightingal3/fig-qa
-- pietrolesci/conj_nli
-- liar
-- sciq
-- head_qa
-- pietrolesci/dnc
+- tasksource/bigbench
+- blimp
+- cos_e
+- cosmos_qa
+- dream
+- openbookqa
+- qasc
 - quartz
+- quail
+- head_qa
+- sciq
+- social_i_qa
+- wiki_hop
 - wiqa
-- code_x_glue_cc_code_refinement
-- Ericwang/promptCoherence
-- joey234/nan-nli
-- hope_edi
-- jnlpba
-- yelp_review_full
-- pietrolesci/recast_white
+- piqa
+- hellaswag
+- pkavumba/balanced-copa
+- 12ml/e-CARE
+- art
+- tasksource/mmlu
+- winogrande
+- codah
+- ai2_arc
+- definite_pronoun_resolution
 - swag
-- banking77
-- cosmos_qa
-- financial_phrasebank
-- hans
-- pietrolesci/fracas
 - math_qa
-- conll2003
-- qasc
-- ncbi_disease
-- mwong/fever-evidence-related
-- YaHi/EffectiveFeedbackStudentWriting
-- ade_corpus_v2
-- amazon_polarity
-- pietrolesci/robust_nli_li_ts
-- super_glue
-- adv_glue
-- Ericwang/promptNLI
-- cos_e
-- launch/open_question_type
-- lex_glue
-- has_part
+- metaeval/utilitarianism
+- mteb/amazon_counterfactual
+- SetFit/insincere-questions
+- SetFit/toxic_conversations
+- turingbench/TuringBench
+- trec
+- tals/vitaminc
+- hope_edi
+- strombergnlp/rumoureval_2019
+- ethos
+- tweet_eval
+- discovery
 - pragmeval
-- sem_eval_2010_task_8
+- silicone
+- lex_glue
+- papluca/language-identification
 - imdb
-- humicroedit
-- sms_spam
+- rotten_tomatoes
+- ag_news
+- yelp_review_full
+- financial_phrasebank
+- poem_sentiment
 - dbpedia_14
-- commonsense_qa
-- hlgd
-- snli
-- hyperpartisan_news_detection
-- google_wellformed_query
-- raquiba/Sarcasm_News_Headline
-- metaeval/recast
-- winogrande
+- amazon_polarity
+- app_reviews
+- hate_speech18
+- sms_spam
+- humicroedit
+- snips_built_in_intents
+- banking77
+- hate_speech_offensive
+- yahoo_answers_topics
+- pacovaldez/stackoverflow-questions
+- zapsdcn/hyperpartisan_news
+- zapsdcn/sciie
+- zapsdcn/citation_intent
+- go_emotions
+- scicite
+- liar
 - relbert/lexical_relation_classification
 - metaeval/linguisticprobing
+- metaeval/crowdflower
+- metaeval/ethics
+- emo
+- google_wellformed_query
+- tweets_hate_speech_detection
+- has_part
+- wnut_17
+- ncbi_disease
+- acronym_identification
+- jnlpba
+- species_800
+- SpeedOfMagic/ontonotes_english
+- blog_authorship_corpus
+- launch/open_question_type
+- health_fact
+- commonsense_qa
+- mc_taco
+- ade_corpus_v2
+- prajjwal1/discosense
+- circa
+- YaHi/EffectiveFeedbackStudentWriting
+- Ericwang/promptSentiment
+- Ericwang/promptNLI
+- Ericwang/promptSpoke
+- Ericwang/promptProficiency
+- Ericwang/promptGrammar
+- Ericwang/promptCoherence
+- PiC/phrase_similarity
+- copenlu/scientific-exaggeration-detection
+- quarel
+- mwong/fever-evidence-related
+- numer_sense
+- dynabench/dynasent
+- raquiba/Sarcasm_News_Headline
+- sem_eval_2010_task_8
+- demo-org/auditor_review
+- medmcqa
+- aqua_rat
+- RuyuanWan/Dynasent_Disagreement
+- RuyuanWan/Politeness_Disagreement
+- RuyuanWan/SBIC_Disagreement
+- RuyuanWan/SChem_Disagreement
+- RuyuanWan/Dilemmas_Disagreement
+- lucasmccabe/logiqa
+- wiki_qa
+- metaeval/cycic_classification
+- metaeval/cycic_multiplechoice
+- metaeval/sts-companion
+- metaeval/commonsense_qa_2.0
+- metaeval/lingnli
+- metaeval/monotonicity-entailment
+- metaeval/arct
+- metaeval/scinli
+- metaeval/naturallogic
+- onestop_qa
+- demelin/moral_stories
+- corypaik/prost
+- aps/dynahate
+- metaeval/syntactic-augmentation-nli
+- metaeval/autotnli
+- lasha-nlp/CONDAQA
+- openai/webgpt_comparisons
+- Dahoas/synthetic-instruct-gptj-pairwise
+- metaeval/scruples
+- metaeval/wouldyourather
+- sileod/attempto-nli
+- metaeval/defeasible-nli
+- metaeval/help-nli
+- metaeval/nli-veridicality-transitivity
+- metaeval/natural-language-satisfiability
+- metaeval/lonli
+- metaeval/dadc-limit-nli
+- ColumbiaNLP/FLUTE
+- metaeval/strategy-qa
+- openai/summarize_from_feedback
+- metaeval/folio
+- metaeval/tomi-nli
+- metaeval/avicenna
+- stanfordnlp/SHP
+- GBaker/MedQA-USMLE-4-options-hf
+- sileod/wikimedqa
+- declare-lab/cicero
+- amydeng2000/CREAK
+- metaeval/mutual
+- inverse-scaling/NeQA
+- inverse-scaling/quote-repetition
+- inverse-scaling/redefine-math
+- metaeval/puzzte
+- metaeval/implicatures
+- race
+- metaeval/spartqa-yn
+- metaeval/spartqa-mchoice
+- metaeval/temporal-nli
 metrics:
 - accuracy
 library_name: transformers