Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging Yiming Ju author Ziyi Ni author Xingrun Xing author Zhixiong Zeng author Hanyu Zhao author Siqi Fan author Zheng Zhang 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 ju-etal-2024-mitigating 10.18653/v1/2024.emnlp-main.892 https://aclanthology.org/2024.emnlp-main.892/ 2024-11 15952 15959