Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models

Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models Zhuoran Jin author Pengfei Cao author Hongbang Yuan author Yubo Chen author Jiexin Xu author Huaijun Li author Xiaojian Jiang author Kang Liu author Jun Zhao 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 jin-etal-2024-cutting 10.18653/v1/2024.findings-acl.70 https://aclanthology.org/2024.findings-acl.70/ 2024-08 1193 1215