Update contamination_report.csv
Browse files- contamination_report.csv +4 -1
contamination_report.csv
CHANGED
|
@@ -463,7 +463,6 @@ bigbio/mednli;;GPT-3.5;model;0.0;0.0;0.0;model-based;https://arxiv.org/pdf/2308.
|
|
| 463 |
RadNLI;;GPT-4;model;0.0;0.0;0.0;model-based;https://arxiv.org/pdf/2308.08493;8
|
| 464 |
RadNLI;;GPT-3.5;model;0.0;0.0;0.0;model-based;https://arxiv.org/pdf/2308.08493;8
|
| 465 |
|
| 466 |
-
|
| 467 |
quac;;GPT-3;model;;99.0;;data-based;https://arxiv.org/abs/2005.14165;
|
| 468 |
rajpurkar/squad_v2;;GPT-3;model;;94.0;;data-based;https://arxiv.org/abs/2005.14165;
|
| 469 |
ucinlp/drop;;GPT-3;model;;93.0;;data-based;https://arxiv.org/abs/2005.14165;
|
|
@@ -503,9 +502,11 @@ Rowan/hellaswag;;GPT-3;model;;2.0;;data-based;https://arxiv.org/abs/2005.14165;
|
|
| 503 |
natural_questions;;GPT-3;model;;;1.0;data-based;https://arxiv.org/abs/2005.14165;
|
| 504 |
Cycled Letters;;GPT-3;model;;1.0;;data-based;https://arxiv.org/abs/2005.14165;
|
| 505 |
SAT Analogies;;GPT-3;model;;1.0;;data-based;https://arxiv.org/abs/2005.14165;
|
|
|
|
| 506 |
EdinburghNLP/xsum;;PaLM 2;model;;;42.0;data-based;https://arxiv.org/abs/2305.10403;
|
| 507 |
csebuetnlp/xlsum;;PaLM 2;model;;;46.9;data-based;https://arxiv.org/abs/2305.10403;
|
| 508 |
wiki_lingua;;PaLM 2;model;;;9.0;data-based;https://arxiv.org/abs/2305.10403;
|
|
|
|
| 509 |
winograd_wsc;;PaLM;model;;;38.5;data-based;https://arxiv.org/abs/2204.02311;
|
| 510 |
rmanluo/RoG-webqsp;;PaLM;model;;;26.7;data-based;https://arxiv.org/abs/2204.02311;
|
| 511 |
super_glue;wsc;PaLM;model;;;36.8;data-based;https://arxiv.org/abs/2204.02311;
|
|
@@ -516,6 +517,7 @@ cimec/lambada;;PaLM;model;;;29.3;data-based;https://arxiv.org/abs/2204.02311;
|
|
| 516 |
super_glue;cb;PaLM;model;;48.2;;data-based;https://arxiv.org/abs/2204.02311;
|
| 517 |
ibragim-bad/arc_easy;;PaLM;model;;;30.4;data-based;https://arxiv.org/abs/2204.02311;
|
| 518 |
ibragim-bad/arc_challenge;;PaLM;model;;;24.7;data-based;https://arxiv.org/abs/2204.02311;
|
|
|
|
| 519 |
winograd_wsc;;GLaM;model;;67.3;;data-based;https://arxiv.org/abs/2112.06905;
|
| 520 |
winogrande;;GLaM;model;;;0.3;data-based;https://arxiv.org/abs/2112.06905;
|
| 521 |
super_glue;wic;GLaM;model;;8.2;;data-based;https://arxiv.org/abs/2112.06905;
|
|
@@ -543,6 +545,7 @@ ibragim-bad/arc_challenge;;GLaM;model;;31.8;;data-based;https://arxiv.org/abs/21
|
|
| 543 |
facebook/anli;dev_r3;GLaM;model;;40.7;;data-based;https://arxiv.org/abs/2112.06905;
|
| 544 |
facebook/anli;dev_r2;GLaM;model;;96.8;;data-based;https://arxiv.org/abs/2112.06905;
|
| 545 |
facebook/anli;dev_r1;GLaM;model;;96.2;;data-based;https://arxiv.org/abs/2112.06905;
|
|
|
|
| 546 |
winogrande;;FLAN;model;;;0.2;data-based;https://arxiv.org/abs/2109.01652;
|
| 547 |
mandarjoshi/trivia_qa;;FLAN;model;;22.8;;data-based;https://arxiv.org/abs/2109.01652;
|
| 548 |
story_cloze;;FLAN;model;;0.4;;data-based;https://arxiv.org/abs/2109.01652;
|
|
|
|
| 463 |
RadNLI;;GPT-4;model;0.0;0.0;0.0;model-based;https://arxiv.org/pdf/2308.08493;8
|
| 464 |
RadNLI;;GPT-3.5;model;0.0;0.0;0.0;model-based;https://arxiv.org/pdf/2308.08493;8
|
| 465 |
|
|
|
|
| 466 |
quac;;GPT-3;model;;99.0;;data-based;https://arxiv.org/abs/2005.14165;
|
| 467 |
rajpurkar/squad_v2;;GPT-3;model;;94.0;;data-based;https://arxiv.org/abs/2005.14165;
|
| 468 |
ucinlp/drop;;GPT-3;model;;93.0;;data-based;https://arxiv.org/abs/2005.14165;
|
|
|
|
| 502 |
natural_questions;;GPT-3;model;;;1.0;data-based;https://arxiv.org/abs/2005.14165;
|
| 503 |
Cycled Letters;;GPT-3;model;;1.0;;data-based;https://arxiv.org/abs/2005.14165;
|
| 504 |
SAT Analogies;;GPT-3;model;;1.0;;data-based;https://arxiv.org/abs/2005.14165;
|
| 505 |
+
|
| 506 |
EdinburghNLP/xsum;;PaLM 2;model;;;42.0;data-based;https://arxiv.org/abs/2305.10403;
|
| 507 |
csebuetnlp/xlsum;;PaLM 2;model;;;46.9;data-based;https://arxiv.org/abs/2305.10403;
|
| 508 |
wiki_lingua;;PaLM 2;model;;;9.0;data-based;https://arxiv.org/abs/2305.10403;
|
| 509 |
+
|
| 510 |
winograd_wsc;;PaLM;model;;;38.5;data-based;https://arxiv.org/abs/2204.02311;
|
| 511 |
rmanluo/RoG-webqsp;;PaLM;model;;;26.7;data-based;https://arxiv.org/abs/2204.02311;
|
| 512 |
super_glue;wsc;PaLM;model;;;36.8;data-based;https://arxiv.org/abs/2204.02311;
|
|
|
|
| 517 |
super_glue;cb;PaLM;model;;48.2;;data-based;https://arxiv.org/abs/2204.02311;
|
| 518 |
ibragim-bad/arc_easy;;PaLM;model;;;30.4;data-based;https://arxiv.org/abs/2204.02311;
|
| 519 |
ibragim-bad/arc_challenge;;PaLM;model;;;24.7;data-based;https://arxiv.org/abs/2204.02311;
|
| 520 |
+
|
| 521 |
winograd_wsc;;GLaM;model;;67.3;;data-based;https://arxiv.org/abs/2112.06905;
|
| 522 |
winogrande;;GLaM;model;;;0.3;data-based;https://arxiv.org/abs/2112.06905;
|
| 523 |
super_glue;wic;GLaM;model;;8.2;;data-based;https://arxiv.org/abs/2112.06905;
|
|
|
|
| 545 |
facebook/anli;dev_r3;GLaM;model;;40.7;;data-based;https://arxiv.org/abs/2112.06905;
|
| 546 |
facebook/anli;dev_r2;GLaM;model;;96.8;;data-based;https://arxiv.org/abs/2112.06905;
|
| 547 |
facebook/anli;dev_r1;GLaM;model;;96.2;;data-based;https://arxiv.org/abs/2112.06905;
|
| 548 |
+
|
| 549 |
winogrande;;FLAN;model;;;0.2;data-based;https://arxiv.org/abs/2109.01652;
|
| 550 |
mandarjoshi/trivia_qa;;FLAN;model;;22.8;;data-based;https://arxiv.org/abs/2109.01652;
|
| 551 |
story_cloze;;FLAN;model;;0.4;;data-based;https://arxiv.org/abs/2109.01652;
|