Dataset Groups Activity Stream Anthropic's HH-RLHF and OpenAI's summarization datasets The dataset used in the paper is the Anthropic's HH-RLHF and OpenAI's summarization datasets. BibTex: @dataset{Shihan_Dou_and_Yan_Liu_and_Enyu_Zhou_and_Songyang_Gao_and_Tianlong_Li_and_Haoxiang_Jia_and_Limao_Xiong_and_Xin_Zhao_and_Junjie_Ye_and_Rui_Zheng_and_Tao_Gui_and_Qi_Zhang_and_Xuanjing_Huang_2024, abstract = {The dataset used in the paper is the Anthropic's HH-RLHF and OpenAI's summarization datasets.}, author = {Shihan Dou and Yan Liu and Enyu Zhou and Songyang Gao and Tianlong Li and Haoxiang Jia and Limao Xiong and Xin Zhao and Junjie Ye and Rui Zheng and Tao Gui and Qi Zhang and Xuanjing Huang}, doi = {10.57702/aauq4m07}, institution = {No Organization}, keyword = {'dialogue generation', 'human feedback', 'reinforcement learning', 'summarization'}, month = {dec}, publisher = {TIB}, title = {Anthropic's HH-RLHF and OpenAI's summarization datasets}, url = {https://service.tib.eu/ldmservice/dataset/anthropic-s-hh-rlhf-and-openai-s-summarization-datasets}, year = {2024} }
