Refusal Lives Downstream of Persona in Chat Models
This paper shows that refusal in instruction-tuned chat models is gated by a compliant persona direction. Interventions on Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct demonstrate that steering compliant persona suppresses refusal (e.g., Llama's refusal rate drops from 97% to 2%), and refusal direction only partially restores refusal in late layers. The findings indicate refusal is expressed downstream of persona computation.
[2606.26161] Refusal Lives Downstream of Persona in Chat Models
[Submitted on 24 Jun 2026]
Title:Refusal Lives Downstream of Persona in Chat Models
View a PDF of the paper titled Refusal Lives Downstream of Persona in Chat Models, by Viola Zhong and 1 other authors
View PDF HTML (experimental)
Abstract:Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but the two have been studied as separate mechanisms. We show they interact: a compliant persona gates refusal. In Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct, we extract a compliant model-persona direction and a refusal direction and intervene on both. Compliant persona steering suppresses refusal -- in Llama, the refusal rate falls from 97% to 2%. Reintroducing the refusal direction partially restores refusal at late layers but not at early ones. Projecting out the persona direction in a late-layer window restores it to baseline; projecting out a random direction does not. Refusal is therefore gated at the late-layer expression stage, downstream of where it is computed. Treating refusal as a single isolated direction misses its dependence on persona.
Comments: Accepted to the ICML 2026 Mechanistic Interpretability workshop
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.26161 [cs.AI]
(or arXiv:2606.26161v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.26161
arXiv-issued DOI via DataCite
Submission history
From: Viola Zhong [view email] [v1] Wed, 24 Jun 2026 04:25:59 UTC (244 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Refusal Lives Downstream of Persona in Chat Models, by Viola Zhong and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs
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?)