Update README.md

README.md

@@ -1,4 +1,294 @@
 ---
+datasets:
+- nyu-mll/glue
+- aps/super_glue
+- facebook/anli
+- tasksource/babi_nli
+- sick
+- snli
+- scitail
+- hans
+- alisawuffles/WANLI
+- tasksource/recast
+- sileod/probability_words_nli
+- joey234/nan-nli
+- pietrolesci/nli_fever
+- pietrolesci/breaking_nli
+- pietrolesci/conj_nli
+- pietrolesci/fracas
+- pietrolesci/dialogue_nli
+- pietrolesci/mpe
+- pietrolesci/dnc
+- pietrolesci/recast_white
+- pietrolesci/joci
+- pietrolesci/robust_nli
+- pietrolesci/robust_nli_is_sd
+- pietrolesci/robust_nli_li_ts
+- pietrolesci/gen_debiased_nli
+- pietrolesci/add_one_rte
+- tasksource/imppres
+- hlgd
+- paws
+- medical_questions_pairs
+- Anthropic/model-written-evals
+- truthful_qa
+- nightingal3/fig-qa
+- tasksource/bigbench
+- blimp
+- cos_e
+- cosmos_qa
+- dream
+- openbookqa
+- qasc
+- quartz
+- quail
+- head_qa
+- sciq
+- social_i_qa
+- wiki_hop
+- wiqa
+- piqa
+- hellaswag
+- pkavumba/balanced-copa
+- 12ml/e-CARE
+- art
+- winogrande
+- codah
+- ai2_arc
+- definite_pronoun_resolution
+- swag
+- math_qa
+- 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
+- silicone
+- lex_glue
+- papluca/language-identification
+- imdb
+- rotten_tomatoes
+- ag_news
+- yelp_review_full
+- financial_phrasebank
+- poem_sentiment
+- dbpedia_14
+- amazon_polarity
+- app_reviews
+- hate_speech18
+- sms_spam
+- humicroedit
+- snips_built_in_intents
+- hate_speech_offensive
+- yahoo_answers_topics
+- pacovaldez/stackoverflow-questions
+- zapsdcn/hyperpartisan_news
+- zapsdcn/sciie
+- zapsdcn/citation_intent
+- go_emotions
+- allenai/scicite
+- liar
+- relbert/lexical_relation_classification
+- tasksource/linguisticprobing
+- tasksource/crowdflower
+- metaeval/ethics
+- emo
+- google_wellformed_query
+- tweets_hate_speech_detection
+- has_part
+- blog_authorship_corpus
+- launch/open_question_type
+- health_fact
+- commonsense_qa
+- mc_taco
+- ade_corpus_v2
+- prajjwal1/discosense
+- circa
+- 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
+- RuyuanWan/Dynasent_Disagreement
+- RuyuanWan/Politeness_Disagreement
+- RuyuanWan/SBIC_Disagreement
+- RuyuanWan/SChem_Disagreement
+- RuyuanWan/Dilemmas_Disagreement
+- lucasmccabe/logiqa
+- wiki_qa
+- tasksource/cycic_classification
+- tasksource/cycic_multiplechoice
+- tasksource/sts-companion
+- tasksource/commonsense_qa_2.0
+- tasksource/lingnli
+- tasksource/monotonicity-entailment
+- tasksource/arct
+- tasksource/scinli
+- tasksource/naturallogic
+- onestop_qa
+- demelin/moral_stories
+- corypaik/prost
+- aps/dynahate
+- metaeval/syntactic-augmentation-nli
+- tasksource/autotnli
+- lasha-nlp/CONDAQA
+- openai/webgpt_comparisons
+- Dahoas/synthetic-instruct-gptj-pairwise
+- metaeval/scruples
+- metaeval/wouldyourather
+- metaeval/defeasible-nli
+- tasksource/help-nli
+- metaeval/nli-veridicality-transitivity
+- tasksource/lonli
+- tasksource/dadc-limit-nli
+- ColumbiaNLP/FLUTE
+- tasksource/strategy-qa
+- openai/summarize_from_feedback
+- tasksource/folio
+- yale-nlp/FOLIO
+- tasksource/tomi-nli
+- tasksource/avicenna
+- stanfordnlp/SHP
+- GBaker/MedQA-USMLE-4-options-hf
+- sileod/wikimedqa
+- declare-lab/cicero
+- amydeng2000/CREAK
+- tasksource/mutual
+- inverse-scaling/NeQA
+- inverse-scaling/quote-repetition
+- inverse-scaling/redefine-math
+- tasksource/puzzte
+- tasksource/implicatures
+- race
+- tasksource/race-c
+- tasksource/spartqa-yn
+- tasksource/spartqa-mchoice
+- tasksource/temporal-nli
+- riddle_sense
+- tasksource/clcd-english
+- maximedb/twentyquestions
+- metaeval/reclor
+- tasksource/counterfactually-augmented-imdb
+- tasksource/counterfactually-augmented-snli
+- metaeval/cnli
+- tasksource/boolq-natural-perturbations
+- metaeval/acceptability-prediction
+- metaeval/equate
+- tasksource/ScienceQA_text_only
+- Jiangjie/ekar_english
+- tasksource/implicit-hate-stg1
+- metaeval/chaos-mnli-ambiguity
+- IlyaGusev/headline_cause
+- tasksource/logiqa-2.0-nli
+- tasksource/oasst2_dense_flat
+- sileod/mindgames
+- metaeval/ambient
+- metaeval/path-naturalness-prediction
+- civil_comments
+- AndyChiang/cloth
+- AndyChiang/dgen
+- tasksource/I2D2
+- webis/args_me
+- webis/Touche23-ValueEval
+- tasksource/starcon
+- PolyAI/banking77
+- tasksource/ConTRoL-nli
+- tasksource/tracie
+- tasksource/sherliic
+- tasksource/sen-making
+- tasksource/winowhy
+- tasksource/robustLR
+- CLUTRR/v1
+- tasksource/logical-fallacy
+- tasksource/parade
+- tasksource/cladder
+- tasksource/subjectivity
+- tasksource/MOH
+- tasksource/VUAC
+- tasksource/TroFi
+- sharc_modified
+- tasksource/conceptrules_v2
+- metaeval/disrpt
+- tasksource/zero-shot-label-nli
+- tasksource/com2sense
+- tasksource/scone
+- tasksource/winodict
+- tasksource/fool-me-twice
+- tasksource/monli
+- tasksource/corr2cause
+- lighteval/lsat_qa
+- tasksource/apt
+- zeroshot/twitter-financial-news-sentiment
+- tasksource/icl-symbol-tuning-instruct
+- tasksource/SpaceNLI
+- sihaochen/propsegment
+- HannahRoseKirk/HatemojiBuild
+- tasksource/regset
+- tasksource/esci
+- lmsys/chatbot_arena_conversations
+- neurae/dnd_style_intents
+- hitachi-nlp/FLD.v2
+- tasksource/SDOH-NLI
+- allenai/scifact_entailment
+- tasksource/feasibilityQA
+- tasksource/simple_pair
+- tasksource/AdjectiveScaleProbe-nli
+- tasksource/resnli
+- tasksource/SpaRTUN
+- tasksource/ReSQ
+- tasksource/semantic_fragments_nli
+- MoritzLaurer/dataset_train_nli
+- tasksource/stepgame
+- tasksource/nlgraph
+- tasksource/oasst2_pairwise_rlhf_reward
+- tasksource/hh-rlhf
+- tasksource/ruletaker
+- qbao775/PARARULE-Plus
+- tasksource/proofwriter
+- tasksource/logical-entailment
+- tasksource/nope
+- tasksource/LogicNLI
+- kiddothe2b/contract-nli
+- AshtonIsNotHere/nli4ct_semeval2024
+- tasksource/lsat-ar
+- tasksource/lsat-rc
+- AshtonIsNotHere/biosift-nli
+- tasksource/brainteasers
+- Anthropic/persuasion
+- erbacher/AmbigNQ-clarifying-question
+- tasksource/SIGA-nli
+- unigram/FOL-nli
+- tasksource/goal-step-wikihow
+- GGLab/PARADISE
+- tasksource/doc-nli
+- tasksource/mctest-nli
+- tasksource/patent-phrase-similarity
+- tasksource/natural-language-satisfiability
+- tasksource/idioms-nli
+- tasksource/lifecycle-entailment
+- nvidia/HelpSteer
+- nvidia/HelpSteer2
+- sadat2307/MSciNLI
+- pushpdeep/UltraFeedback-paired
+- tasksource/AES2-essay-scoring
+- tasksource/english-grading
+- tasksource/wice
+- Dzeniks/hover
+- sileod/missing-item-prediction
+- tasksource/tasksource_dpo_pairs
 language:
 - en
 - zh
@@ -9,8 +299,6 @@ tags:
 - vqa
 - text
 - audio
-datasets:
-- synthetic-dataset
 metrics:
 - accuracy
 - bleu