Contamination results updated based on ``https://arxiv.org/abs/2311.06233``

Contamination results for IMDB, AG News, Yelp, RTE, WNLI, SAMSum, and XSum. Also, new contamination levels were found for HumanEval, DROP, and GSM8k datasets. GPT-4 and GPT3.5 are the base models in experiments.

contamination_report.csv

@@ -1,5 +1,23 @@
 Evaluation Dataset;Subset;Contaminated Source;Model or corpus;Train Split;Development Split;Test Split;Approach;Reference;PR
 
+gsm8k;;GPT-4;model;79.00;;;model-based;https://arxiv.org/abs/2311.06233;8
+ucinlp/drop;;GPT-4;model;;44.00;;model-based;https://arxiv.org/abs/2311.06233;8
+openai_humaneval;;GPT-4;model;;;56.71;model-based;https://arxiv.org/abs/2311.06233;8
+imdb;;GPT-4;model;;;82.00;model-based;https://arxiv.org/abs/2311.06233;8
+imdb;;GPT-3.5;model;;;55.00;model-based;https://arxiv.org/abs/2311.06233;8
+ag_news;;GPT-4;model;;;91.00;model-based;https://arxiv.org/abs/2311.06233;8
+ag_news;;GPT-3.5;model;;;82.00;model-based;https://arxiv.org/abs/2311.06233;8
+yelp_review_full;;GPT-4;model;;;80.00;model-based;https://arxiv.org/abs/2311.06233;8
+yelp_review_full;;GPT-3.5;model;;;13.00;model-based;https://arxiv.org/abs/2311.06233;8
+nyu-mll/glue;rte;GPT-4;model;;60.00;;model-based;https://arxiv.org/abs/2311.06233;8
+nyu-mll/glue;rte;GPT-3.5;model;;71.00;;model-based;https://arxiv.org/abs/2311.06233;8
+nyu-mll/glue;wnli;GPT-4;model;;50.70;;model-based;https://arxiv.org/abs/2311.06233;8
+nyu-mll/glue;wnli;GPT-3.5;model;;12.68;;model-based;https://arxiv.org/abs/2311.06233;8
+samsum;;GPT-4;model;;;77.00;model-based;https://arxiv.org/abs/2311.06233;8
+samsum;;GPT-3.5;model;;;74.00;model-based;https://arxiv.org/abs/2311.06233;8
+EdinburghNLP/xsum;;GPT-4;model;;;95.00;model-based;https://arxiv.org/abs/2311.06233;8
+EdinburghNLP/xsum;;GPT-3.5;model;;;79.00;model-based;https://arxiv.org/abs/2311.06233;8
+
 conll2003;;GPT-3.5;model;100.0;100.0;100.0;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
 nyu-mll/glue;mnli;GPT-3.5;model;100.0;100.0;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
 rajpurkar/squad_v2;;GPT-3.5;model;100.0;100.0;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7