GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets

GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets Oh Joon Kwon author Daiki E Matsunaga author Kee-Eung Kim author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication kwon-etal-2024-gdpo 10.18653/v1/2024.emnlp-main.951 https://aclanthology.org/2024.emnlp-main.951/ 2024-11 17120 17139