Dataset Groups Activity Stream HH-RLHF The HH-RLHF dataset is a human preference dataset for reinforcement learning from human feedback. BibTex: @dataset{Shusheng_Xu_and_Wei_Fu_and_Jiaxuan_Gao_and_Wenjie_Ye_and_Weilin_Liu_and_Zhiyu_Mei_and_Guangju_Wang_and_Chao_Yu_and_Yi_Wu_2024, abstract = {The HH-RLHF dataset is a human preference dataset for reinforcement learning from human feedback.}, author = {Shusheng Xu and Wei Fu and Jiaxuan Gao and Wenjie Ye and Weilin Liu and Zhiyu Mei and Guangju Wang and Chao Yu and Yi Wu}, doi = {10.57702/xvs2nhsa}, institution = {No Organization}, keyword = {'HH-RLHF', 'Human Feedback', 'Reinforcement Learning', 'harmlessness', 'helpfulness', 'human preference', 'language models', 'question answering', 'single entity', 'single relation'}, month = {dec}, publisher = {TIB}, title = {HH-RLHF}, url = {https://service.tib.eu/ldmservice/dataset/hh-rlhf}, year = {2024} }
