Work

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment

Year: 2025

Type: conference-paper

Abstract: With rapid advancement and increasing accessibility of LLMs, fine-tuning aligned models has become a critical step for adapting them to real-world applications, which makes the safety of this fine-tuning process more important than ever.However, recent studies have highlighted a critical challenge: even when fine-tuning with benign datasets, the safety alignment of aligned LLMs can be compromised, making them more susceptible to malicious instructions.In this paper, we show that fine-tuning datasets often contain safetydegrading samples that are not easily identifiable on the surface.These samples can easily degrade the safety alignment of LLMs during fine-tuning.To address this issue, we propose LARF, a Layer-Aware Representation Filtering method.This method identifies safety-sensitive layers within the LLM and leverages data representations to detect safetydegrading data samples in the fine-tuning dataset.Experimental results demonstrate that LARF can efficiently and effectively identify safety-degrading data.After removing such data, the safety alignment degradation caused by fine-tuning is mitigated.Please see our code at https://github.com/LLLeoLi/LARF.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/2025.emnlp-main.406