Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models

Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models Xinran Zhao author Hongming Zhang author Xiaoman Pan author Wenlin Yao author Dong Yu author Tongshuang Wu author Jianshu Chen author 2024-08 text Findings of the Association for Computational Linguistics: ACL 2024 Lun-Wei Ku editor Andre Martins editor Vivek Srikumar editor Association for Computational Linguistics Bangkok, Thailand conference publication zhao-etal-2024-fact 10.18653/v1/2024.findings-acl.515 https://aclanthology.org/2024.findings-acl.515/ 2024-08 8702 8718