Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Puning, Wang, Qizhou, Huang, Zhuo, Liu, Tongliang, Zhang, Chengqi, Han, Bo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912398728757248
author Yang, Puning
Wang, Qizhou
Huang, Zhuo
Liu, Tongliang
Zhang, Chengqi
Han, Bo
author_facet Yang, Puning
Wang, Qizhou
Huang, Zhuo
Liu, Tongliang
Zhang, Chengqi
Han, Bo
contents Loss reweighting has shown significant benefits for machine unlearning with large language models (LLMs). However, their exact functionalities are left unclear and the optimal strategy remains an open question, thus impeding the understanding and improvement of existing methodologies. In this paper, we identify two distinct goals of loss reweighting, namely, Saturation and Importance -- the former indicates that those insufficiently optimized data should be emphasized, while the latter stresses some critical data that are most influential for loss minimization. To study their usefulness, we design specific reweighting strategies for each goal and evaluate their respective effects on unlearning. We conduct extensive empirical analyses on well-established benchmarks, and summarize some important observations as follows: (i) Saturation enhances efficacy more than importance-based reweighting, and their combination can yield additional improvements. (ii) Saturation typically allocates lower weights to data with lower likelihoods, whereas importance-based reweighting does the opposite. (iii) The efficacy of unlearning is also largely influenced by the smoothness and granularity of the weight distributions. Based on these findings, we propose SatImp, a simple reweighting method that combines the advantages of both saturation and importance. Empirical results on extensive datasets validate the efficacy of our method, potentially bridging existing research gaps and indicating directions for future research. Our code is available at https://github.com/tmlr-group/SatImp.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11953
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
Yang, Puning
Wang, Qizhou
Huang, Zhuo
Liu, Tongliang
Zhang, Chengqi
Han, Bo
Machine Learning
Artificial Intelligence
Loss reweighting has shown significant benefits for machine unlearning with large language models (LLMs). However, their exact functionalities are left unclear and the optimal strategy remains an open question, thus impeding the understanding and improvement of existing methodologies. In this paper, we identify two distinct goals of loss reweighting, namely, Saturation and Importance -- the former indicates that those insufficiently optimized data should be emphasized, while the latter stresses some critical data that are most influential for loss minimization. To study their usefulness, we design specific reweighting strategies for each goal and evaluate their respective effects on unlearning. We conduct extensive empirical analyses on well-established benchmarks, and summarize some important observations as follows: (i) Saturation enhances efficacy more than importance-based reweighting, and their combination can yield additional improvements. (ii) Saturation typically allocates lower weights to data with lower likelihoods, whereas importance-based reweighting does the opposite. (iii) The efficacy of unlearning is also largely influenced by the smoothness and granularity of the weight distributions. Based on these findings, we propose SatImp, a simple reweighting method that combines the advantages of both saturation and importance. Empirical results on extensive datasets validate the efficacy of our method, potentially bridging existing research gaps and indicating directions for future research. Our code is available at https://github.com/tmlr-group/SatImp.
title Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.11953