Added Contamination Evidence on MMLU of ChatGPT/GPT4 from "Investigating data contamination in modern benchmarks for large language models" (#10)

- Update contamination_report.csv (383926d5dc6ddec32216652947950efd9f1b0df8)
- Update contamination_report.csv (5ecf89dce1728b3e6c0329a44752442431a30ba3)
- Update contamination_report.csv (4666215baa7d58f706e11b0940259d73bba8ae2c)
- Update contamination_report.csv (77f5a8da1d7951a49843f9dae6dbfe0905db469c)
- Update contamination_report.csv (eb87bf5b3f5b7f5ba69862fbf90fccec27c00e2f)
- Merge branch 'main' of https://huggingface.co/spaces/CONDA-Workshop/Data-Contamination-Report into pr/10 (18d798a286845b7f8a62d786d3240c65af0ffe07)


Co-authored-by: Ameya Prabhu <[email protected]>

contamination_report.csv

@@ -477,6 +477,30 @@ EdinburghNLP/xsum;;GPT-3.5;model;0.0;;100.0;model-based;https://arxiv.org/abs/23
 bigbio/mednli;;GPT-4;model;0.0;0.0;0.0;model-based;https://arxiv.org/abs/2308.08493;8
 bigbio/mednli;;GPT-3.5;model;0.0;0.0;0.0;model-based;https://arxiv.org/abs/2308.08493;8
 
+RadNLI;;GPT-4;model;0.0;0.0;0.0;model-based;https://arxiv.org/pdf/2308.08493;8
+RadNLI;;GPT-3.5;model;0.0;0.0;0.0;model-based;https://arxiv.org/pdf/2308.08493;8
+
+
+cais/mmlu;;GPT-3.5;model;;;52.0;model-based;https://arxiv.org/abs/2311.09783;10
+winogrande;;GPT-3.5;model;;;9.0;model-based;https://arxiv.org/abs/2311.09783;10
+truthful_qa;;GPT-3.5;model;;;12.0;model-based;https://arxiv.org/abs/2311.09783;10
+allenai/openbookqa;;GPT-3.5;model;;;1.0;model-based;https://arxiv.org/abs/2311.09783;10
+
+cais/mmlu;;GPT-4;model;;;57.0;model-based;https://arxiv.org/abs/2311.09783;10
+truthful_qa;;GPT-4;model;;;10.0;model-based;https://arxiv.org/abs/2311.09783;10
+winogrande;;GPT-4;model;;;12.0;model-based;https://arxiv.org/abs/2311.09783;10
+allenai/openbookqa;;GPT-4;model;;;1.0;model-based;https://arxiv.org/abs/2311.09783;10
+Rowan/hellaswag;;GPT-4;model;;;2.0;model-based;https://arxiv.org/abs/2311.09783;10
+
+
+allenai/openbookqa;;LLaMa 2-13B;model;;;4.0;model-based;https://arxiv.org/abs/2311.09783;10
+truthful_qa;;LLaMa 2-13B;model;;;2.0;model-based;https://arxiv.org/abs/2311.09783;10
+winogrande;;LLaMa 2-13B;model;;;1.0;model-based;https://arxiv.org/abs/2311.09783;10
+
+truthful_qa;;Mistral-7B;model;;;15.0;model-based;https://arxiv.org/abs/2311.09783;10
+allenai/openbookqa;;Mistral-7B;model;;;10.0;model-based;https://arxiv.org/abs/2311.09783;10
+winogrande;;Mistral-7B;model;;;3.0;model-based;https://arxiv.org/abs/2311.09783;10
+cais/mmlu;;Mistral-7B;model;;;1.0;model-based;https://arxiv.org/abs/2311.09783;10
 RadNLI;;GPT-4;model;0.0;0.0;0.0;model-based;https://arxiv.org/abs/2308.08493;8
 RadNLI;;GPT-3.5;model;0.0;0.0;0.0;model-based;https://arxiv.org/abs/2308.08493;8
 RadNLI;;GPT-4;model;0.0;0.0;0.0;model-based;https://arxiv.org/abs/2308.08493;8