|
dataset,fewshots,prompt,metric,value
|
|
e2e_nlg_cleaned,0,generate_text_restaurant,rouge2_fmeasure,0.027201662156796255
|
|
e2e_nlg_cleaned,0,median,rouge2_fmeasure,0.027201662156796255
|
|
e2e_nlg_cleaned,1,generate_text_restaurant,rouge2_fmeasure,0.10002146341400579
|
|
e2e_nlg_cleaned,1,median,rouge2_fmeasure,0.10002146341400579
|
|
e2e_nlg_cleaned,2,generate_text_restaurant,rouge2_fmeasure,0.11837013500076157
|
|
e2e_nlg_cleaned,2,median,rouge2_fmeasure,0.11837013500076157
|
|
e2e_nlg_cleaned,3,generate_text_restaurant,rouge2_fmeasure,0.12236707177425063
|
|
e2e_nlg_cleaned,3,median,rouge2_fmeasure,0.12236707177425063
|
|
e2e_nlg_cleaned,4,generate_text_restaurant,rouge2_fmeasure,0.12862161964342028
|
|
e2e_nlg_cleaned,4,median,rouge2_fmeasure,0.12862161964342028
|
|
e2e_nlg_cleaned,5,generate_text_restaurant,rouge2_fmeasure,0.12861734204623188
|
|
e2e_nlg_cleaned,5,median,rouge2_fmeasure,0.12861734204623188
|
|
e2e_nlg_cleaned,5,average,multiple,0.1041998823392444
|
|
gem_xsum,0,article_DOC_summary,rouge2_fmeasure,0.04090748442736069
|
|
gem_xsum,0,median,rouge2_fmeasure,0.04090748442736069
|
|
gem_xsum,1,article_DOC_summary,rouge2_fmeasure,0.024638353865890434
|
|
gem_xsum,1,median,rouge2_fmeasure,0.024638353865890434
|
|
gem_xsum,2,article_DOC_summary,rouge2_fmeasure,0.021605793985650032
|
|
gem_xsum,2,median,rouge2_fmeasure,0.021605793985650032
|
|
gem_xsum,3,article_DOC_summary,rouge2_fmeasure,0.020403012896272645
|
|
gem_xsum,3,median,rouge2_fmeasure,0.020403012896272645
|
|
gem_xsum,4,article_DOC_summary,rouge2_fmeasure,0.00536187053653973
|
|
gem_xsum,4,median,rouge2_fmeasure,0.00536187053653973
|
|
gem_xsum,5,article_DOC_summary,rouge2_fmeasure,0.0
|
|
gem_xsum,5,median,rouge2_fmeasure,0.0
|
|
gem_xsum,5,average,multiple,0.018819419285285587
|
|
web_nlg_en,0,PALM_prompt,rouge2_fmeasure,0.03514871886969164
|
|
web_nlg_en,0,median,rouge2_fmeasure,0.03514871886969164
|
|
web_nlg_en,1,PALM_prompt,rouge2_fmeasure,0.0348005109489672
|
|
web_nlg_en,1,median,rouge2_fmeasure,0.0348005109489672
|
|
web_nlg_en,2,PALM_prompt,rouge2_fmeasure,0.036072521136247385
|
|
web_nlg_en,2,median,rouge2_fmeasure,0.036072521136247385
|
|
web_nlg_en,3,PALM_prompt,rouge2_fmeasure,0.03505346120993315
|
|
web_nlg_en,3,median,rouge2_fmeasure,0.03505346120993315
|
|
web_nlg_en,4,PALM_prompt,rouge2_fmeasure,0.03527561542480963
|
|
web_nlg_en,4,median,rouge2_fmeasure,0.03527561542480963
|
|
web_nlg_en,5,PALM_prompt,rouge2_fmeasure,0.034951021231894634
|
|
web_nlg_en,5,median,rouge2_fmeasure,0.034951021231894634
|
|
web_nlg_en,5,average,multiple,0.03521697480359061
|
|
wiki_lingua_en,0,tldr_en,rouge2_fmeasure,0.026484542226918303
|
|
wiki_lingua_en,0,median,rouge2_fmeasure,0.026484542226918303
|
|
wiki_lingua_en,1,tldr_en,rouge2_fmeasure,0.026405299879801242
|
|
wiki_lingua_en,1,median,rouge2_fmeasure,0.026405299879801242
|
|
wiki_lingua_en,2,tldr_en,rouge2_fmeasure,0.028604389417761292
|
|
wiki_lingua_en,2,median,rouge2_fmeasure,0.028604389417761292
|
|
wiki_lingua_en,3,tldr_en,rouge2_fmeasure,0.025681636061568994
|
|
wiki_lingua_en,3,median,rouge2_fmeasure,0.025681636061568994
|
|
wiki_lingua_en,4,tldr_en,rouge2_fmeasure,0.009405169337583598
|
|
wiki_lingua_en,4,median,rouge2_fmeasure,0.009405169337583598
|
|
wiki_lingua_en,5,tldr_en,rouge2_fmeasure,0.0013965027873250944
|
|
wiki_lingua_en,5,median,rouge2_fmeasure,0.0013965027873250944
|
|
wiki_lingua_en,5,average,multiple,0.019662923285159752
|
|
|