Dataset Groups Activity Stream WMDP The dataset used in the paper is a benchmark contamination detection dataset, which contains questions and answers from various benchmarks. BibTex: @dataset{Huixuan_Zhang_and_Yun_Lin_and_Xiaojun_Wan_2024, abstract = {The dataset used in the paper is a benchmark contamination detection dataset, which contains questions and answers from various benchmarks.}, author = {Huixuan Zhang and Yun Lin and Xiaojun Wan}, doi = {10.57702/yof3ukr3}, institution = {No Organization}, keyword = {'benchmark contamination', 'large language models', 'question answering'}, month = {dec}, publisher = {TIB}, title = {WMDP}, url = {https://service.tib.eu/ldmservice/dataset/wmdp}, year = {2024} }
