Skip to content
AI News HubLIVE
Original source2 min read

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

Summary

The paper characterizes a multi-stage safety circuit behind LLM refusal behavior—harmful detection heads, safety neurons, and refusal heads—and validates it with circuit-guided weight scaling, raising attack-time safety rates by 26.5% across six LLMs with only a 1.7% accuracy drop on standard benchmarks.

SourcearXiv Computational LinguisticsAuthor: Kuan-Lin Chu, Chung-En Sun, Tsui-Wei Weng
From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 30 Aug 2026]

Title:From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

View a PDF of the paper titled From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling, by Kuan-Lin Chu and 2 other authors

View PDF HTML (experimental)

Abstract:Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the internal mechanisms by which safety behaviors are implemented remain poorly understood. We study LLM safety from a mechanistic interpretability perspective and characterize a multi-stage *safety circuit* that organizes refusal behavior, consisting of (i) $\textbf{Harmful Detection Heads}$ that respond to harmful inputs, (ii) $\textbf{Safety Neurons}$ that mediate and stabilize safety signals in the residual stream, and (iii) $\textbf{Refusal Heads}$ that translate these signals into safe response generation. Using targeted attention-head and neuron-level interventions, we provide causal evidence consistent with this circuit organization, showing that suppressing upstream Harmful Detection Heads disrupts downstream refusal behavior and that safety neurons mediate this interaction. We validate that this decomposition recurs across multiple LLM architectures and adversarial attack settings, and use simple, architecture-preserving weight scaling as a mechanistic probe to test its functional relevance. Across six LLMs, circuit-guided scaling improves safety rates under attacks by 26.5%, while incurring only a 1.7% accuracy drop across four standard benchmarks. Overall, our results support a circuit-level interpretation of LLM safety and suggest that mechanistic abstractions can reveal stable and transferable patterns underlying aligned behavior.

Comments: Accepted to Findings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)

Cite as: arXiv:2609.00051 [cs.CL]

(or arXiv:2609.00051v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.00051

arXiv-issued DOI via DataCite

Submission history

From: Kuan-Lin Chu [view email] [v1] Sun, 30 Aug 2026 08:01:42 UTC (2,290 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling, by Kuan-Lin Chu and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-09

Change to browse by:

cs cs.AI cs.CY

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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 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?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Identifies a three-stage safety circuit: harmful detection heads, safety neurons, and refusal heads
  • Intervention experiments give causal evidence that suppressing upstream detection heads disrupts downstream refusal
  • Circuit-guided weight scaling improves safety under attack by 26.5% with a 1.7% accuracy cost
  • The decomposition recurs across multiple architectures and attack settings; accepted to EMNLP 2026 Findings

Highlights and analysis are generated automatically and may contain errors. Check the original source.