[2607.05842] Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Software Engineering

arXiv:2607.05842 (cs)

[Submitted on 7 Jul 2026]

Title:Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

Authors:Mingchen Li, Meikang Qiu, Zifan Peng, Heng Fan, Song Fu, Junhua Ding, Yunhe Feng<br>View a PDF of the paper titled Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis, by Mingchen Li and 6 other authors

View PDF<br>HTML (experimental)

Abstract:Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerability-analysis terminology needed for legitimate code review, triage, and repair can closely resemble terminology associated with misuse. Existing safety and cybersecurity evaluations are difficult to interpret in this setting because they often compare unrelated model families, thereby conflating safety behavior with differences in architecture, scale, training data, and deployment. To isolate this factor, we study safety state: whether refusal behavior remains intact (Aligned) or has been refusal-ablated (Abliterated) within same-lineage models. We ask how this safety state affects defensive utility across software-security workflows. We compare aligned instruction-tuned models with publicly released refusal-ablated descendants from two model families, Gemma and Qwen. We evaluate Aligned and Abliterated states on vulnerability detection, CWE attribution, vulnerable-line localization, root-cause localization, and executable patch validation. We further treat prompt wording as a controlled framing dimension: prompts begin with neutral code-review language, add authorization context, and vary the density of cybersecurity terminology. In a Gemma-based Java/Vul4J repair-validation study, Abliterated achieves higher early-stage validation rates, with 67.8%, 65.0%, and 32.8% of patches judged usable, successfully applied, and successfully compiled, respectively, compared with 29.9%, 24.9%, and 9.0% for Aligned. In the Qwen pair, Abliterated improves localization performance, increasing line-level F1 from 2.08% to 3.91% and Top-1 accuracy from 4.10% to 6.95%. These findings suggest that evaluations of LLM-based security assistants should jointly measure whether models respond, whether their usable responses are correct, and whether their outputs remain actionable across the engineering workflow.

Subjects:

Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)

Cite as:<br>arXiv:2607.05842 [cs.SE]

(or<br>arXiv:2607.05842v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2607.05842

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Mingchen Li [view email]<br>[v1]<br>Tue, 7 Jul 2026 05:04:48 UTC (2,059 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis, by Mingchen Li and 6 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.SE

next >

new<br>recent<br>| 2026-07

Change to browse by:

cs<br>cs.AI<br>cs.CR

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

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?)

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...