Update contamination_report.csv
#4
by
borgr
- opened
- contamination_report.csv +7 -0
contamination_report.csv
CHANGED
@@ -1,5 +1,12 @@
|
|
1 |
Evaluation Dataset;Subset;Contaminated Source;Model or corpus;Train Split;Development Split;Test Split;Approach;Reference;PR
|
2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
|
4 |
UCLNLP/adversarial_qa;adversarialQA;allenai/c4;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
|
5 |
UCLNLP/adversarial_qa;adversarialQA;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
|
|
|
1 |
Evaluation Dataset;Subset;Contaminated Source;Model or corpus;Train Split;Development Split;Test Split;Approach;Reference;PR
|
2 |
|
3 |
+
conll2003;;GPT-4;Model;;;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;4
|
4 |
+
nyu-mll/glue;;GPT-4;Model;;;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;4
|
5 |
+
rajpurkar/squad_v2;;GPT-4;Model;;;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;4
|
6 |
+
https://catalog.ldc.upenn.edu/LDC2006T06;;GPT-4;Model;;;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;4
|
7 |
+
quac;;GPT-4;Model;;;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;4
|
8 |
+
natural_questions;;GPT-4;Model;;;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;4
|
9 |
+
google/boolq;;GPT-4;Model;;;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;4
|
10 |
|
11 |
UCLNLP/adversarial_qa;adversarialQA;allenai/c4;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
|
12 |
UCLNLP/adversarial_qa;adversarialQA;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
|