RankMean: Module-Level Importance Score for Merging Fine-tuned LLM Models

RankMean: Module-Level Importance Score for Merging Fine-tuned LLM Models Gabriel Perin author Xuxi Chen author Shusen Liu author Bhavya Kailkhura author Zhangyang Wang author Brian Gallagher 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 perin-etal-2024-rankmean 10.18653/v1/2024.findings-acl.104 https://aclanthology.org/2024.findings-acl.104/ 2024-08 1776 1782