Dataset Groups Activity Stream MT-bench The dataset used in the paper is MT-bench, which is an LLM-based automated evaluation metric comprising 80 challenging questions. BibTex: @dataset{Wenxuan_Zhou_and_Ravi_Agrawal_and_Shujian_Zhang_and_Sathish_Reddy_Indurthi_and_Sanqiang_Zhao_and_Kaiqiang_Song_and_Silei_Xu_and_Chenguang_Zhu_2024, abstract = {The dataset used in the paper is MT-bench, which is an LLM-based automated evaluation metric comprising 80 challenging questions.}, author = {Wenxuan Zhou and Ravi Agrawal and Shujian Zhang and Sathish Reddy Indurthi and Sanqiang Zhao and Kaiqiang Song and Silei Xu and Chenguang Zhu}, doi = {10.57702/fe7w0o4l}, institution = {No Organization}, keyword = {'LLM', 'MT-bench', 'question answering'}, month = {dec}, publisher = {TIB}, title = {MT-bench}, url = {https://service.tib.eu/ldmservice/dataset/mt-bench}, year = {2024} }
