Dataset Groups Activity Stream Alpaca Eval 2 The dataset used in the paper is Alpaca Eval 2, which is an automated metric that measures LLMs' alignment with human preferences. 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 Alpaca Eval 2, which is an automated metric that measures LLMs' alignment with human preferences.}, 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/fqx2uypf}, institution = {No Organization}, keyword = {'Alpaca Eval 2', 'LLM', 'instruction following'}, month = {dec}, publisher = {TIB}, title = {Alpaca Eval 2}, url = {https://service.tib.eu/ldmservice/dataset/alpaca-eval-2}, year = {2024} }
