Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, Fei Huang. RRHF: Rank Responses to Align Language Models with Human Feedback. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]
@inproceedings{YuanYTWHH23, title = {RRHF: Rank Responses to Align Language Models with Human Feedback}, author = {Hongyi Yuan and Zheng Yuan and Chuanqi Tan and Wei Wang and Songfang Huang and Fei Huang}, year = {2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/23e6f78bdec844a9f7b6c957de2aae91-Abstract-Conference.html}, researchr = {https://researchr.org/publication/YuanYTWHH23}, cites = {0}, citedby = {0}, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, }