微調重參數化能保住安全對齊

Computer Science > Machine Learning arXiv:2610.

26443 (cs) [Submitted on 19 Oct 2026 (v1), last revised 20 Oct 2026 (this version, v2)] Title:Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation Authors:Min-Seong Kim, Jongbok Won, Jeesup Park, Yonghee Choi, Dong-Jun Han View a PDF of the paper titled Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation, by Min-Seong Kim and 4 other authors View PDF HTML (experimental) Abstract:Fine-tuning large language models (LLMs) on downstream tasks often weakens their previously aligned safety behavior, creating an inherent trade-off between task adaptation and safety preservation.

Existing approaches attempt to mitigate this issue by identifying safety-relevant neurons, layers, or update directions in the original parameter space.

However, safety-related information is often distributed across many directions in this space, causing downstream updates to overwrite parameters that encode safety behavior.

We propose WSR-Tune, a Weight Space Reparameterization-based fine-tuning framework that preserves safety during downstream adaptation.

Our approach constructs a safety-conditioned basis and reparameterizes the weight matrices such that safety-relevant information becomes concentrated in a small subset of directions.

We then identify safety-critical directions and freeze them in the reparameterized space, while updating the remaining complementary directions for downstream adaptation.

By explicitly structuring the parameter space to disentangle safety and task information, our method reduces interference between objectives and enables simultaneous preservation of safety and improvement in downstream performance.

Experimental results show that our method achieves a more favorable trade-off between downstream performance and safety retention, demonstrating its effectiveness for reliable LLM fine-tuning.Comments: 32 pages, 5 figures.Accepted at NeurIPS 2026(spotlight) Subjects: Machine Learning (cs.

LG); Artificial Intelligence (cs.AI) Cite as: arXiv:2610.26443 [cs.LG] (or arXiv:2610.26443v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2610.

26443 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Minseong Kim [view email] [v1] Mon, 19 Oct 2026 14:02:31 UTC (2,260 KB) [v2] Tue, 20 Oct 2026 05:28:24 UTC (2,260 KB) Full-text links: Access Paper: View a PDF of the paper titled Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation, by Min-Seong Kim and 4 other authorsView PDFHTML (experimental)TeX Source view license Additional Features Audio Summary Current browse context: cs.

LG < prev | next > new | recent | 2026-10 Change to browse by: cs cs.AI References & Citations SciXGoogle Scholar Semantic Scholar export BibTeX citation Loading...BibTeX formatted citation × loading...

Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.

ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?

) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.

AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?

) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community?Learn more about arXivLabs.Which authors of this paper are endorsers?| Disable MathJax (What is MathJax?)