Updates
Browse files- contamination_report.csv +30 -30
- postprocessing.py +1 -1
contamination_report.csv
CHANGED
|
@@ -244,43 +244,19 @@ natural_questions;;FLAN;;model;;3.2;;data-based;https://arxiv.org/abs/2109.01652
|
|
| 244 |
natural_questions;;GLaM;;model;;3.9;;data-based;https://arxiv.org/abs/2112.06905;13
|
| 245 |
natural_questions;;GPT-3;;model;;;1.0;data-based;https://arxiv.org/abs/2005.14165;13
|
| 246 |
|
| 247 |
-
nyu-mll/glue;BoolQ;allenai/c4;;corpus;;;2.4;data-based;https://arxiv.org/abs/2104.08758;6
|
| 248 |
-
|
| 249 |
-
nyu-mll/glue;CoLA;allenai/c4;;corpus;;;14.4;data-based;https://arxiv.org/abs/2104.08758;6
|
| 250 |
-
|
| 251 |
-
nyu-mll/glue;MNLI-hypothesis;allenai/c4;;corpus;;;14.2;data-based;https://arxiv.org/abs/2104.08758;6
|
| 252 |
-
|
| 253 |
-
nyu-mll/glue;MNLI-premise;allenai/c4;;corpus;;;15.2;data-based;https://arxiv.org/abs/2104.08758;6
|
| 254 |
-
|
| 255 |
-
nyu-mll/glue;MRPC-sentence-1;allenai/c4;;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
|
| 256 |
-
|
| 257 |
-
nyu-mll/glue;MRPC-sentence-2;allenai/c4;;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
|
| 258 |
-
|
| 259 |
-
nyu-mll/glue;QNLI-question;allenai/c4;;corpus;;;1.8;data-based;https://arxiv.org/abs/2104.08758;6
|
| 260 |
-
|
| 261 |
-
nyu-mll/glue;QNLI-sentence;allenai/c4;;corpus;;;53.6;data-based;https://arxiv.org/abs/2104.08758;6
|
| 262 |
-
|
| 263 |
-
nyu-mll/glue;RTE-sentence-1;allenai/c4;;corpus;;;6;data-based;https://arxiv.org/abs/2104.08758;6
|
| 264 |
-
|
| 265 |
-
nyu-mll/glue;RTE-sentence-2;allenai/c4;;corpus;;;10.8;data-based;https://arxiv.org/abs/2104.08758;6
|
| 266 |
-
|
| 267 |
-
nyu-mll/glue;SST-2;allenai/c4;;corpus;;;11;data-based;https://arxiv.org/abs/2104.08758;6
|
| 268 |
-
|
| 269 |
-
nyu-mll/glue;STS-B-sentence-1;allenai/c4;;corpus;;;18.3;data-based;https://arxiv.org/abs/2104.08758;6
|
| 270 |
-
|
| 271 |
-
nyu-mll/glue;STS-B-sentence-2;allenai/c4;;corpus;;;18.6;data-based;https://arxiv.org/abs/2104.08758;6
|
| 272 |
-
|
| 273 |
-
nyu-mll/glue;WNLI-sentence-1;allenai/c4;;corpus;;;4.8;data-based;https://arxiv.org/abs/2104.08758;6
|
| 274 |
-
|
| 275 |
-
nyu-mll/glue;WNLI-sentence-2;allenai/c4;;corpus;;;2.1;data-based;https://arxiv.org/abs/2104.08758;6
|
| 276 |
-
|
| 277 |
nyu-mll/glue;ax;EleutherAI/pile;;corpus;;;5.07;data-based;https://arxiv.org/abs/2310.20707;2
|
| 278 |
nyu-mll/glue;ax;allenai/c4;;corpus;;;1.99;data-based;https://arxiv.org/abs/2310.20707;2
|
| 279 |
nyu-mll/glue;ax;oscar-corpus/OSCAR-2301;;corpus;;;1.45;data-based;https://arxiv.org/abs/2310.20707;2
|
| 280 |
nyu-mll/glue;ax;togethercomputer/RedPajama-Data-V2;;corpus;;;6.16;data-based;https://arxiv.org/abs/2310.20707;2
|
| 281 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 282 |
nyu-mll/glue;mnli;GPT-3.5;;model;100.0;100.0;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
|
| 283 |
|
|
|
|
|
|
|
| 284 |
nyu-mll/glue;mnli-matched;EleutherAI/pile;;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;2
|
| 285 |
nyu-mll/glue;mnli-matched;allenai/c4;;corpus;;;1.65;data-based;https://arxiv.org/abs/2310.20707;2
|
| 286 |
nyu-mll/glue;mnli-matched;oscar-corpus/OSCAR-2301;;corpus;;;1.77;data-based;https://arxiv.org/abs/2310.20707;2
|
|
@@ -291,16 +267,26 @@ nyu-mll/glue;mnli-mismatched;allenai/c4;;corpus;;;1.73;data-based;https://arxiv.
|
|
| 291 |
nyu-mll/glue;mnli-mismatched;oscar-corpus/OSCAR-2301;;corpus;;;1.91;data-based;https://arxiv.org/abs/2310.20707;2
|
| 292 |
nyu-mll/glue;mnli-mismatched;togethercomputer/RedPajama-Data-V2;;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;2
|
| 293 |
|
|
|
|
|
|
|
| 294 |
nyu-mll/glue;mrpc;EleutherAI/pile;;corpus;;;0.64;data-based;https://arxiv.org/abs/2310.20707;2
|
| 295 |
nyu-mll/glue;mrpc;allenai/c4;;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
|
| 296 |
nyu-mll/glue;mrpc;oscar-corpus/OSCAR-2301;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
|
| 297 |
nyu-mll/glue;mrpc;togethercomputer/RedPajama-Data-V2;;corpus;;;1.16;data-based;https://arxiv.org/abs/2310.20707;2
|
| 298 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 299 |
nyu-mll/glue;qnli;EleutherAI/pile;;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;2
|
| 300 |
nyu-mll/glue;qnli;allenai/c4;;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
|
| 301 |
nyu-mll/glue;qnli;oscar-corpus/OSCAR-2301;;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
|
| 302 |
nyu-mll/glue;qnli;togethercomputer/RedPajama-Data-V2;;corpus;;;1.21;data-based;https://arxiv.org/abs/2310.20707;2
|
| 303 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 304 |
nyu-mll/glue;rte;EleutherAI/pile;;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
|
| 305 |
nyu-mll/glue;rte;GPT-3.5;;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
|
| 306 |
nyu-mll/glue;rte;GPT-3.5;;model;;71.00;;model-based;https://arxiv.org/abs/2311.06233;8
|
|
@@ -310,11 +296,21 @@ nyu-mll/glue;rte;allenai/c4;;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.
|
|
| 310 |
nyu-mll/glue;rte;oscar-corpus/OSCAR-2301;;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;2
|
| 311 |
nyu-mll/glue;rte;togethercomputer/RedPajama-Data-V2;;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;2
|
| 312 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 313 |
nyu-mll/glue;stsb;EleutherAI/pile;;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;2
|
| 314 |
nyu-mll/glue;stsb;allenai/c4;;corpus;;;3.48;data-based;https://arxiv.org/abs/2310.20707;2
|
| 315 |
nyu-mll/glue;stsb;oscar-corpus/OSCAR-2301;;corpus;;;3.12;data-based;https://arxiv.org/abs/2310.20707;2
|
| 316 |
nyu-mll/glue;stsb;togethercomputer/RedPajama-Data-V2;;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;2
|
| 317 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 318 |
nyu-mll/glue;wnli;EleutherAI/pile;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
|
| 319 |
nyu-mll/glue;wnli;GPT-3.5;;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
|
| 320 |
nyu-mll/glue;wnli;GPT-3.5;;model;;12.68;;model-based;https://arxiv.org/abs/2311.06233;8
|
|
@@ -324,6 +320,10 @@ nyu-mll/glue;wnli;allenai/c4;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310
|
|
| 324 |
nyu-mll/glue;wnli;oscar-corpus/OSCAR-2301;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
|
| 325 |
nyu-mll/glue;wnli;togethercomputer/RedPajama-Data-V2;;corpus;;;2.05;data-based;https://arxiv.org/abs/2310.20707;2
|
| 326 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 327 |
openai_humaneval;;EleutherAI/pile;;corpus;;;12.2;data-based;https://arxiv.org/abs/2403.04811;12
|
| 328 |
openai_humaneval;;EleutherAI/pile;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
|
| 329 |
openai_humaneval;;GPT-3.5-turbo;0613;model;;;23.79;model-based;https://arxiv.org/abs/2402.15938;16
|
|
|
|
| 244 |
natural_questions;;GLaM;;model;;3.9;;data-based;https://arxiv.org/abs/2112.06905;13
|
| 245 |
natural_questions;;GPT-3;;model;;;1.0;data-based;https://arxiv.org/abs/2005.14165;13
|
| 246 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
nyu-mll/glue;ax;EleutherAI/pile;;corpus;;;5.07;data-based;https://arxiv.org/abs/2310.20707;2
|
| 248 |
nyu-mll/glue;ax;allenai/c4;;corpus;;;1.99;data-based;https://arxiv.org/abs/2310.20707;2
|
| 249 |
nyu-mll/glue;ax;oscar-corpus/OSCAR-2301;;corpus;;;1.45;data-based;https://arxiv.org/abs/2310.20707;2
|
| 250 |
nyu-mll/glue;ax;togethercomputer/RedPajama-Data-V2;;corpus;;;6.16;data-based;https://arxiv.org/abs/2310.20707;2
|
| 251 |
|
| 252 |
+
nyu-mll/glue;boolq;allenai/c4;;corpus;;;2.4;data-based;https://arxiv.org/abs/2104.08758;6
|
| 253 |
+
|
| 254 |
+
nyu-mll/glue;cola;allenai/c4;;corpus;;;14.4;data-based;https://arxiv.org/abs/2104.08758;6
|
| 255 |
+
|
| 256 |
nyu-mll/glue;mnli;GPT-3.5;;model;100.0;100.0;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
|
| 257 |
|
| 258 |
+
nyu-mll/glue;mnli-hypothesis;allenai/c4;;corpus;;;14.2;data-based;https://arxiv.org/abs/2104.08758;6
|
| 259 |
+
|
| 260 |
nyu-mll/glue;mnli-matched;EleutherAI/pile;;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;2
|
| 261 |
nyu-mll/glue;mnli-matched;allenai/c4;;corpus;;;1.65;data-based;https://arxiv.org/abs/2310.20707;2
|
| 262 |
nyu-mll/glue;mnli-matched;oscar-corpus/OSCAR-2301;;corpus;;;1.77;data-based;https://arxiv.org/abs/2310.20707;2
|
|
|
|
| 267 |
nyu-mll/glue;mnli-mismatched;oscar-corpus/OSCAR-2301;;corpus;;;1.91;data-based;https://arxiv.org/abs/2310.20707;2
|
| 268 |
nyu-mll/glue;mnli-mismatched;togethercomputer/RedPajama-Data-V2;;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;2
|
| 269 |
|
| 270 |
+
nyu-mll/glue;mnli-premise;allenai/c4;;corpus;;;15.2;data-based;https://arxiv.org/abs/2104.08758;6
|
| 271 |
+
|
| 272 |
nyu-mll/glue;mrpc;EleutherAI/pile;;corpus;;;0.64;data-based;https://arxiv.org/abs/2310.20707;2
|
| 273 |
nyu-mll/glue;mrpc;allenai/c4;;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
|
| 274 |
nyu-mll/glue;mrpc;oscar-corpus/OSCAR-2301;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
|
| 275 |
nyu-mll/glue;mrpc;togethercomputer/RedPajama-Data-V2;;corpus;;;1.16;data-based;https://arxiv.org/abs/2310.20707;2
|
| 276 |
|
| 277 |
+
nyu-mll/glue;mrpc-sentence-1;allenai/c4;;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
|
| 278 |
+
|
| 279 |
+
nyu-mll/glue;mrpc-sentence-2;allenai/c4;;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
|
| 280 |
+
|
| 281 |
nyu-mll/glue;qnli;EleutherAI/pile;;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;2
|
| 282 |
nyu-mll/glue;qnli;allenai/c4;;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
|
| 283 |
nyu-mll/glue;qnli;oscar-corpus/OSCAR-2301;;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
|
| 284 |
nyu-mll/glue;qnli;togethercomputer/RedPajama-Data-V2;;corpus;;;1.21;data-based;https://arxiv.org/abs/2310.20707;2
|
| 285 |
|
| 286 |
+
nyu-mll/glue;qnli-question;allenai/c4;;corpus;;;1.8;data-based;https://arxiv.org/abs/2104.08758;6
|
| 287 |
+
|
| 288 |
+
nyu-mll/glue;qnli-sentence;allenai/c4;;corpus;;;53.6;data-based;https://arxiv.org/abs/2104.08758;6
|
| 289 |
+
|
| 290 |
nyu-mll/glue;rte;EleutherAI/pile;;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
|
| 291 |
nyu-mll/glue;rte;GPT-3.5;;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
|
| 292 |
nyu-mll/glue;rte;GPT-3.5;;model;;71.00;;model-based;https://arxiv.org/abs/2311.06233;8
|
|
|
|
| 296 |
nyu-mll/glue;rte;oscar-corpus/OSCAR-2301;;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;2
|
| 297 |
nyu-mll/glue;rte;togethercomputer/RedPajama-Data-V2;;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;2
|
| 298 |
|
| 299 |
+
nyu-mll/glue;rte-sentence-1;allenai/c4;;corpus;;;6;data-based;https://arxiv.org/abs/2104.08758;6
|
| 300 |
+
|
| 301 |
+
nyu-mll/glue;rte-sentence-2;allenai/c4;;corpus;;;10.8;data-based;https://arxiv.org/abs/2104.08758;6
|
| 302 |
+
|
| 303 |
+
nyu-mll/glue;sst2;allenai/c4;;corpus;;;11;data-based;https://arxiv.org/abs/2104.08758;6
|
| 304 |
+
|
| 305 |
nyu-mll/glue;stsb;EleutherAI/pile;;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;2
|
| 306 |
nyu-mll/glue;stsb;allenai/c4;;corpus;;;3.48;data-based;https://arxiv.org/abs/2310.20707;2
|
| 307 |
nyu-mll/glue;stsb;oscar-corpus/OSCAR-2301;;corpus;;;3.12;data-based;https://arxiv.org/abs/2310.20707;2
|
| 308 |
nyu-mll/glue;stsb;togethercomputer/RedPajama-Data-V2;;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;2
|
| 309 |
|
| 310 |
+
nyu-mll/glue;stsb-sentence-1;allenai/c4;;corpus;;;18.3;data-based;https://arxiv.org/abs/2104.08758;6
|
| 311 |
+
|
| 312 |
+
nyu-mll/glue;stsb-sentence-2;allenai/c4;;corpus;;;18.6;data-based;https://arxiv.org/abs/2104.08758;6
|
| 313 |
+
|
| 314 |
nyu-mll/glue;wnli;EleutherAI/pile;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
|
| 315 |
nyu-mll/glue;wnli;GPT-3.5;;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
|
| 316 |
nyu-mll/glue;wnli;GPT-3.5;;model;;12.68;;model-based;https://arxiv.org/abs/2311.06233;8
|
|
|
|
| 320 |
nyu-mll/glue;wnli;oscar-corpus/OSCAR-2301;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
|
| 321 |
nyu-mll/glue;wnli;togethercomputer/RedPajama-Data-V2;;corpus;;;2.05;data-based;https://arxiv.org/abs/2310.20707;2
|
| 322 |
|
| 323 |
+
nyu-mll/glue;wnli-sentence-1;allenai/c4;;corpus;;;4.8;data-based;https://arxiv.org/abs/2104.08758;6
|
| 324 |
+
|
| 325 |
+
nyu-mll/glue;wnli-sentence-2;allenai/c4;;corpus;;;2.1;data-based;https://arxiv.org/abs/2104.08758;6
|
| 326 |
+
|
| 327 |
openai_humaneval;;EleutherAI/pile;;corpus;;;12.2;data-based;https://arxiv.org/abs/2403.04811;12
|
| 328 |
openai_humaneval;;EleutherAI/pile;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
|
| 329 |
openai_humaneval;;GPT-3.5-turbo;0613;model;;;23.79;model-based;https://arxiv.org/abs/2402.15938;16
|
postprocessing.py
CHANGED
|
@@ -35,7 +35,7 @@ def main():
|
|
| 35 |
if key != past_key:
|
| 36 |
f.write("\n")
|
| 37 |
past_key = key
|
| 38 |
-
line = line[:3] +
|
| 39 |
f.write(";".join(line) + "\n")
|
| 40 |
|
| 41 |
|
|
|
|
| 35 |
if key != past_key:
|
| 36 |
f.write("\n")
|
| 37 |
past_key = key
|
| 38 |
+
line = line[:3] + line[3:]
|
| 39 |
f.write(";".join(line) + "\n")
|
| 40 |
|
| 41 |
|