[Submitted on 5 Nov 2026]
Title:Forcing a Letter Suppresses Refusal: Mechanistic Evidence from WMDP
View a PDF of the paper titled Forcing a Letter Suppresses Refusal: Mechanistic Evidence from WMDP, by Stepan Epifantsev and 4 other authors
View PDF HTML (experimental)
Abstract:Safety benchmarks for large language models (LLMs) commonly use multiple-choice question (MCQ) format. However, prior studies documented that MCQ format reduces refusal rates, which may significantly affect the safety behavior of the model. We provide a first mechanistic explanation of this effect on the Weapons of Mass Destruction Proxy (WMDP) dataset across two models - Llama-3.1-8B and Qwen3-8B. First, we use the tuned lens technique to show that when processing MCQ the model commits to an answer-letter token very quickly, which is in contrast to the gradual refusal build-up in open-ended formats. Additionally, we observe that activations on the MCQ format lie roughly 3x further from the refusal direction, compared with their open-ended counterparts. Moreover, ablating the attention heads that carry the MCQ format answer increases the refusal, which is a direct evidence that the MCQ answer-selection competes with refusal. These findings indicate that MCQ safety scores primarily measure knowledge capabilities and do not assess the safety-mechanisms.
Comments: Accepted to BlackboxNLP 2026 (EMNLP 2026 workshop). 17 pages, 15 figures
Subjects:
Computation and Language (cs.CL); Machine Learning (cs.LG)
Cite as: arXiv:2611.08639 [cs.CL]
(or arXiv:2611.08639v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2611.08639
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Stepan Epifantsev [view email] [v1] Thu, 5 Nov 2026 19:36:44 UTC (4,997 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Forcing a Letter Suppresses Refusal: Mechanistic Evidence from WMDP, by Stepan Epifantsev and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Additional Features
Audio Summary
Current browse context:
cs.CL
new | recent | 2026-11
Change to browse by:
cs cs.LG
References & Citations
SciX
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?)