Saved in:
Bibliographic Details
Main Authors: Li, Hao, Li, Lijun, Lu, Zhenghao, Wei, Xianyi, Li, Rui, Shao, Jing, Sha, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.18631
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911077266096128
author Li, Hao
Li, Lijun
Lu, Zhenghao
Wei, Xianyi
Li, Rui
Shao, Jing
Sha, Lei
author_facet Li, Hao
Li, Lijun
Lu, Zhenghao
Wei, Xianyi
Li, Rui
Shao, Jing
Sha, Lei
contents 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 seemingly benign downstream datasets, the safety of aligned LLMs can be compromised, making them more susceptible to malicious instructions. In this paper, we show that fine-tuning datasets often contain samples with safety-degrading features that are not easily identifiable on the surface. These samples can significantly 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 their representations to detect which data samples in the post-training dataset contain safety-degrading features. Experimental results demonstrate that LARF can effectively identify benign data with safety-degrading features. After removing such data, the safety alignment degradation caused by fine-tuning is mitigated. Please see our code at https://github.com/LLLeoLi/LARF.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18631
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
Li, Hao
Li, Lijun
Lu, Zhenghao
Wei, Xianyi
Li, Rui
Shao, Jing
Sha, Lei
Cryptography and Security
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 seemingly benign downstream datasets, the safety of aligned LLMs can be compromised, making them more susceptible to malicious instructions. In this paper, we show that fine-tuning datasets often contain samples with safety-degrading features that are not easily identifiable on the surface. These samples can significantly 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 their representations to detect which data samples in the post-training dataset contain safety-degrading features. Experimental results demonstrate that LARF can effectively identify benign data with safety-degrading features. After removing such data, the safety alignment degradation caused by fine-tuning is mitigated. Please see our code at https://github.com/LLLeoLi/LARF.
title Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
topic Cryptography and Security
url https://arxiv.org/abs/2507.18631