Saved in:
Bibliographic Details
Main Authors: Bach, Thong, Nguyen-Tang, Thanh, Nguyen, Dung, Le, Thao Minh, Tran, Truyen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.18039
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908669703094272
author Bach, Thong
Nguyen-Tang, Thanh
Nguyen, Dung
Le, Thao Minh
Tran, Truyen
author_facet Bach, Thong
Nguyen-Tang, Thanh
Nguyen, Dung
Le, Thao Minh
Tran, Truyen
contents Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a notable property: fine-tuned models preserve the geometric structure of their loss landscapes concerning harmful content, regardless of the fine-tuning method employed. This suggests that safety behaviors are not erased but shifted to less influential regions of the parameter space. Building on this insight, we propose a curvature-aware alignment restoration method that leverages influence functions and second-order optimization to selectively increase loss on harmful inputs while preserving task performance. By navigating the shared geometry between base and fine-tuned models, our method discourages unsafe outputs while preserving task-relevant performance, avoiding full reversion and enabling precise, low-impact updates. Extensive evaluations across multiple model families and adversarial settings show that our approach efficiently reduces harmful responses while maintaining or even improving utility and few-shot learning performance.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18039
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Curvature-Aware Safety Restoration In LLMs Fine-Tuning
Bach, Thong
Nguyen-Tang, Thanh
Nguyen, Dung
Le, Thao Minh
Tran, Truyen
Machine Learning
Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a notable property: fine-tuned models preserve the geometric structure of their loss landscapes concerning harmful content, regardless of the fine-tuning method employed. This suggests that safety behaviors are not erased but shifted to less influential regions of the parameter space. Building on this insight, we propose a curvature-aware alignment restoration method that leverages influence functions and second-order optimization to selectively increase loss on harmful inputs while preserving task performance. By navigating the shared geometry between base and fine-tuned models, our method discourages unsafe outputs while preserving task-relevant performance, avoiding full reversion and enabling precise, low-impact updates. Extensive evaluations across multiple model families and adversarial settings show that our approach efficiently reduces harmful responses while maintaining or even improving utility and few-shot learning performance.
title Curvature-Aware Safety Restoration In LLMs Fine-Tuning
topic Machine Learning
url https://arxiv.org/abs/2511.18039