evaluation_val/merged.csv

dataset,prompt,metric,value
amazon_reviews_multi_en,prompt_body_title_to_star,accuracy,0.4774
amazon_reviews_multi_en,prompt_review_to_star,accuracy,0.4246
amazon_reviews_multi_en,prompt_title_to_star,accuracy,0.3018
amazon_reviews_multi_en,median,accuracy,0.4246
amazon_reviews_multi_es,prompt_body_title_to_star,accuracy,0.4024
amazon_reviews_multi_es,prompt_review_to_star,accuracy,0.3892
amazon_reviews_multi_es,prompt_title_to_star,accuracy,0.252
amazon_reviews_multi_es,median,accuracy,0.3892
amazon_reviews_multi_fr,prompt_body_title_to_star,accuracy,0.4004
amazon_reviews_multi_fr,prompt_review_to_star,accuracy,0.3838
amazon_reviews_multi_fr,prompt_title_to_star,accuracy,0.2736
amazon_reviews_multi_fr,median,accuracy,0.3838
amazon_reviews_multi_zh,prompt_body_title_to_star,accuracy,0.3524
amazon_reviews_multi_zh,prompt_review_to_star,accuracy,0.3444
amazon_reviews_multi_zh,prompt_title_to_star,accuracy,0.2596
amazon_reviews_multi_zh,median,accuracy,0.3444
aqua_rat_raw,Answer questions from options,accuracy,0.2283464566929134
aqua_rat_raw,answer_quiz,accuracy,0.24803149606299213
aqua_rat_raw,select_the_best_option,accuracy,0.20078740157480315
aqua_rat_raw,median,accuracy,0.2283464566929134
art_None,choose_hypothesis,accuracy,0.5039164490861618
art_None,choose_hypothesis_believable,accuracy,0.4934725848563969
art_None,choose_hypothesis_desc,accuracy,0.4993472584856397
art_None,choose_hypothesis_likely,accuracy,0.5006527415143603
art_None,choose_hypothesis_options,accuracy,0.5065274151436031
art_None,median,accuracy,0.5006527415143603
banking77_None,direct_to_which_department,accuracy,0.14805194805194805
banking77_None,help_page_topic,accuracy,0.19285714285714287
banking77_None,rephrase_as_banking_term,accuracy,0.20454545454545456
banking77_None,median,accuracy,0.19285714285714287
blbooksgenre_title_genre_classifiction,classify,accuracy,0.25172811059907835
blbooksgenre_title_genre_classifiction,multi-choice,accuracy,0.25057603686635943
blbooksgenre_title_genre_classifiction,premise_context_first,accuracy,0.7494239631336406
blbooksgenre_title_genre_classifiction,median,accuracy,0.25172811059907835
blimp_adjunct_island,grammatical_between_1_2,accuracy,0.609
blimp_adjunct_island,grammatical_between_A_B,accuracy,0.512
blimp_adjunct_island,grammatical_which_one_1_2,accuracy,0.571
blimp_adjunct_island,single_sentence_bad_yes_no,accuracy,0.523
blimp_adjunct_island,single_sentence_good_yes_no,accuracy,0.5
blimp_adjunct_island,median,accuracy,0.523
climate_fever_None,claim_and_all_supporting_evidences,accuracy,0.30944625407166126
climate_fever_None,fifth_evidence_and_claim_itemization,accuracy,0.10358306188925082
climate_fever_None,first_evidence_and_claim_itemization,accuracy,0.09771986970684039
climate_fever_None,second_evidence_and_claim_itemization,accuracy,0.10618892508143322
climate_fever_None,third_evidence_claim_pair,accuracy,0.0996742671009772
climate_fever_None,median,accuracy,0.10358306188925082
codah_codah,affirmative_instruction_after_sentence_and_choices,accuracy,0.24603746397694526
codah_codah,affirmative_instruction_before_sentence_and_choices,accuracy,0.23919308357348704
codah_codah,interrogative_instruction_after_sentence_and_choices,accuracy,0.24351585014409222
codah_codah,median,accuracy,0.24351585014409222
commonsense_qa_None,answer_given_question_without_options,accuracy,0.42424242424242425
commonsense_qa_None,most_suitable_answer,accuracy,0.38493038493038495
commonsense_qa_None,question_answering,accuracy,0.389025389025389
commonsense_qa_None,median,accuracy,0.389025389025389
conv_ai_3_None,ambiguous,accuracy,0.39040207522697795
conv_ai_3_None,clarification_needed,accuracy,0.39040207522697795
conv_ai_3_None,directly_answer,accuracy,0.6095979247730221
conv_ai_3_None,score_give_number,accuracy,0.021184608733246867
conv_ai_3_None,score_how_much,accuracy,0.03156074362300043
conv_ai_3_None,median,accuracy,0.39040207522697795
craigslist_bargains_None,best deal,accuracy,0.440536013400335
craigslist_bargains_None,good deal for seller,accuracy,0.5192629815745393
craigslist_bargains_None,good deal for seller no list price,accuracy,0.7236180904522613
craigslist_bargains_None,good deal for seller no list price implicit,accuracy,0.23785594639865998
craigslist_bargains_None,median,accuracy,0.47989949748743715
emotion_None,answer_question_with_emotion_label,accuracy,0.324
emotion_None,answer_with_class_label,accuracy,0.22
emotion_None,choose_the_best_emotion_label,accuracy,0.3875
emotion_None,reply_with_emoation_label,accuracy,0.424
emotion_None,median,accuracy,0.35575
financial_phrasebank_sentences_allagree,bullish_neutral_bearish,accuracy,0.31051236749116606
financial_phrasebank_sentences_allagree,complementary_industries,accuracy,0.14885159010600707
financial_phrasebank_sentences_allagree,sentiment,accuracy,0.3480565371024735
financial_phrasebank_sentences_allagree,share_price_option,accuracy,0.2928445229681979
financial_phrasebank_sentences_allagree,word_comes_to_mind,accuracy,0.21024734982332155
financial_phrasebank_sentences_allagree,median,accuracy,0.2928445229681979
glue_cola,Following sentence acceptable,accuracy,0.6797698945349953
glue_cola,Make sense yes no,accuracy,0.5781399808245445
glue_cola,Previous sentence acceptable,accuracy,0.5992329817833174
glue_cola,editing,accuracy,0.49185043144774687
glue_cola,is_this_correct,accuracy,0.3077660594439118
glue_cola,median,accuracy,0.5781399808245445
glue_sst2,following positive negative,accuracy,0.8314220183486238
glue_sst2,happy or mad,accuracy,0.8371559633027523
glue_sst2,positive negative after,accuracy,0.8096330275229358
glue_sst2,review,accuracy,0.8979357798165137
glue_sst2,said,accuracy,0.8853211009174312
glue_sst2,median,accuracy,0.8371559633027523
head_qa_en,multiple_choice_a_and_q_en,accuracy,0.2759882869692533
head_qa_en,multiple_choice_a_and_q_with_context_en,accuracy,0.27159590043923865
head_qa_en,multiple_choice_q_and_a_en,accuracy,0.2767203513909224
head_qa_en,multiple_choice_q_and_a_index_en,accuracy,0.2591508052708638
head_qa_en,multiple_choice_q_and_a_index_with_context_en,accuracy,0.24377745241581258
head_qa_en,median,accuracy,0.27159590043923865
head_qa_es,multiple_choice_a_and_q_en,accuracy,0.25036603221083453
head_qa_es,multiple_choice_a_and_q_with_context_en,accuracy,0.24597364568081992
head_qa_es,multiple_choice_q_and_a_en,accuracy,0.26281112737920936
head_qa_es,multiple_choice_q_and_a_index_en,accuracy,0.25109809663250365
head_qa_es,multiple_choice_q_and_a_index_with_context_en,accuracy,0.24743777452415813
head_qa_es,median,accuracy,0.25036603221083453
health_fact_None,claim_explanation_classification,accuracy,0.5681632653061225
health_fact_None,claim_veracity_classification_after_reading_I_believe,accuracy,0.1510204081632653
health_fact_None,claim_veracity_classification_tell_me,accuracy,0.4563265306122449
health_fact_None,median,accuracy,0.4563265306122449
hlgd_None,is_same_event_editor_asks,accuracy,0.6578057032382794
hlgd_None,is_same_event_interrogative_talk,accuracy,0.6428226196230062
hlgd_None,is_same_event_refer,accuracy,0.7249879168680522
hlgd_None,is_same_event_with_time_interrogative_related,accuracy,0.6863218946350894
hlgd_None,is_same_event_with_time_interrogative_talk,accuracy,0.6863218946350894
hlgd_None,median,accuracy,0.6863218946350894
hyperpartisan_news_detection_byarticle,consider_does_it_follow_a_hyperpartisan_argumentation,accuracy,0.6310077519379845
hyperpartisan_news_detection_byarticle,consider_it_exhibits_extreme_one_sidedness,accuracy,0.6310077519379845
hyperpartisan_news_detection_byarticle,consume_with_caution,accuracy,0.6325581395348837
hyperpartisan_news_detection_byarticle,extreme_left_wing_or_right_wing,accuracy,0.5829457364341085
hyperpartisan_news_detection_byarticle,follows_hyperpartisan_argumentation,accuracy,0.6201550387596899
hyperpartisan_news_detection_byarticle,median,accuracy,0.6310077519379845
liar_None,Given statement guess category,accuracy,0.19314641744548286
liar_None,median,accuracy,0.19314641744548286
lince_sa_spaeng,express sentiment,accuracy,0.5535233996772458
lince_sa_spaeng,negation template,accuracy,0.16460462614308768
lince_sa_spaeng,original poster expressed sentiment,accuracy,0.5438407746100054
lince_sa_spaeng,sentiment trying to express,accuracy,0.5384615384615384
lince_sa_spaeng,the author seem,accuracy,0.5368477676169984
lince_sa_spaeng,median,accuracy,0.5384615384615384
math_qa_None,choose_correct_og,accuracy,0.21608040201005024
math_qa_None,first_choice_then_problem,accuracy,0.19631490787269681
math_qa_None,gre_problem,accuracy,0.20971524288107202
math_qa_None,pick_the_correct,accuracy,0.21206030150753769
math_qa_None,problem_set_type,accuracy,0.2793969849246231
math_qa_None,median,accuracy,0.21206030150753769
mlsum_es,layman_summ_es,bleu,0.027120352148581234
mlsum_es,palm_prompt,bleu,0.028540407645253642
mlsum_es,summarise_this_in_es_few_sentences,bleu,0.02865384931959682
mlsum_es,median,bleu,0.028540407645253642
movie_rationales_None,Evidences + review,accuracy,0.975
movie_rationales_None,Evidences sentiment classification,accuracy,0.975
movie_rationales_None,Standard binary sentiment analysis,accuracy,0.875
movie_rationales_None,median,accuracy,0.975
mwsc_None,in-the-sentence,accuracy,0.573170731707317
mwsc_None,in-the-sentence-question-first,accuracy,0.524390243902439
mwsc_None,is-correct,accuracy,0.5121951219512195
mwsc_None,options-or,accuracy,0.5365853658536586
mwsc_None,what-think,accuracy,0.5121951219512195
mwsc_None,median,accuracy,0.524390243902439
onestop_english_None,ara_context,accuracy,0.3403880070546737
onestop_english_None,assess,accuracy,0.3350970017636684
onestop_english_None,determine_reading_level_from_the_first_three_sentences,accuracy,0.345679012345679
onestop_english_None,esl_context,accuracy,0.328042328042328
onestop_english_None,esl_variation,accuracy,0.32275132275132273
onestop_english_None,median,accuracy,0.3350970017636684
poem_sentiment_None,guess_sentiment_without_options_variation_1,accuracy,0.2571428571428571
poem_sentiment_None,most_appropriate_sentiment,accuracy,0.3238095238095238
poem_sentiment_None,positive_or_negative_sentiment_variation_1,accuracy,0.2571428571428571
poem_sentiment_None,positive_or_negative_sentiment_variation_2,accuracy,0.29523809523809524
poem_sentiment_None,question_answer_format,accuracy,0.3333333333333333
poem_sentiment_None,median,accuracy,0.29523809523809524
pubmed_qa_pqa_labeled,Long Answer to Final Decision,accuracy,0.635
pubmed_qa_pqa_labeled,Question Answering (Short),accuracy,0.543
pubmed_qa_pqa_labeled,median,accuracy,0.589
riddle_sense_None,answer_given_question_without_options,accuracy,0.39862879529872675
riddle_sense_None,most_suitable_answer,accuracy,0.24877571008814886
riddle_sense_None,question_answering,accuracy,0.24191968658178256
riddle_sense_None,question_to_answer_index,accuracy,0.1929480901077375
riddle_sense_None,median,accuracy,0.24534769833496572
scicite_None,Classify intent,accuracy,0.17903930131004367
scicite_None,Classify intent (choices first),accuracy,0.15065502183406113
scicite_None,Classify intent (select choice),accuracy,0.15611353711790393
scicite_None,Classify intent w/section (select choice),accuracy,0.21724890829694324
scicite_None,can_describe,accuracy,0.259825327510917
scicite_None,median,accuracy,0.17903930131004367
selqa_answer_selection_analysis,is-he-talking-about,accuracy,0.8866242038216561
selqa_answer_selection_analysis,make-sense-rand,accuracy,0.8738853503184714
selqa_answer_selection_analysis,which-answer-1st-vs-random,accuracy,0.5171974522292994
selqa_answer_selection_analysis,would-make-sense-qu-rand,accuracy,0.8802547770700637
selqa_answer_selection_analysis,median,accuracy,0.8770700636942675
snips_built_in_intents_None,categorize_query,accuracy,0.3597560975609756
snips_built_in_intents_None,categorize_query_brief,accuracy,0.5396341463414634
snips_built_in_intents_None,intent_query,accuracy,0.1676829268292683
snips_built_in_intents_None,query_intent,accuracy,0.4603658536585366
snips_built_in_intents_None,voice_intent,accuracy,0.39634146341463417
snips_built_in_intents_None,median,accuracy,0.39634146341463417
wmt14_fr_en_en-fr,a_good_translation-en-fr-source+target,bleu,0.023458085666003575
wmt14_fr_en_en-fr,a_good_translation-en-fr-target,bleu,0.021816396665585328
wmt14_fr_en_en-fr,gpt3-en-fr,bleu,0.00025997559795041045
wmt14_fr_en_en-fr,version-en-fr-target,bleu,0.02227540952829272
wmt14_fr_en_en-fr,xglm-en-fr-target,bleu,0.06208490978871131
wmt14_fr_en_en-fr,median,bleu,0.02227540952829272
wmt14_fr_en_fr-en,a_good_translation-fr-en-source+target,bleu,0.25380925876631605
wmt14_fr_en_fr-en,a_good_translation-fr-en-target,bleu,0.16622960261108521
wmt14_fr_en_fr-en,gpt3-fr-en,bleu,0.008644457350404656
wmt14_fr_en_fr-en,version-fr-en-target,bleu,0.1606615213941368
wmt14_fr_en_fr-en,xglm-fr-en-target,bleu,0.1760990614881427
wmt14_fr_en_fr-en,median,bleu,0.16622960261108521
wmt14_hi_en_en-hi,a_good_translation-en-hi-source+target,bleu,0.004949179557007594
wmt14_hi_en_en-hi,a_good_translation-en-hi-target,bleu,0.0026204531297437587
wmt14_hi_en_en-hi,gpt-3-en-hi-target,bleu,1.0125186357154061e-26
wmt14_hi_en_en-hi,version-en-hi-target,bleu,0.002859269911787752
wmt14_hi_en_en-hi,xglm-en-hi-target,bleu,0.000291688799662918
wmt14_hi_en_en-hi,median,bleu,0.0026204531297437587
wmt14_hi_en_hi-en,a_good_translation-hi-en-source+target,bleu,0.110920558209937
wmt14_hi_en_hi-en,a_good_translation-hi-en-target,bleu,0.07969255346070397
wmt14_hi_en_hi-en,gpt-3-hi-en-target,bleu,1.815212789755798e-57
wmt14_hi_en_hi-en,version-hi-en-target,bleu,0.10179796760814867
wmt14_hi_en_hi-en,xglm-hi-en-target,bleu,0.08420322693635622
wmt14_hi_en_hi-en,median,bleu,0.08420322693635622
multiple,average,multiple,0.37171450318227334