Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
Activation steering can shift LLM behaviour, but standard evaluations don't test whether sycophancy reduction also suppresses factual agreement. The authors introduce dual-stance evaluation, finding that while sycophantic and factual agreement are in distinct subspaces, the steering direction projects equally onto both, reducing both. This reveals a gap: readable representations may not be writable.
[2606.11205] Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
[Submitted on 22 Apr 2026]
Title:Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
View a PDF of the paper titled Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention, by Matthew James Buchan
View PDF HTML (experimental)
Abstract:Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements. We introduce dual-stance evaluation, which tests both stances of each topic, and apply it to centroid-difference steering on Llama-3-8B-Instruct. We find a dissociation: the model represents sycophantic and factual agreement in geometrically distinct subspaces, yet the steering direction projects equally onto both and cannot differentially target either. The direction accordingly reduces agreement with factually correct statements (e.g. that the Earth is round) as well as sycophantic ones. All other static properties of the two activation groups are matched, suggesting the behavioural dissociation arises from generation dynamics or from finer-grained structure that residual-stream analysis cannot resolve. The pattern illustrates a general gap: representations that are readable from activations may not be writable through them.
Comments: 18 pages, 9 figures, accepted to TAIS 2026
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2606.11205 [cs.LG]
(or arXiv:2606.11205v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.11205
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Matthew Buchan [view email] [v1] Wed, 22 Apr 2026 13:49:34 UTC (160 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention, by Matthew James Buchan
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-06
Change to browse by:
cs cs.AI cs.CL
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?)
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?)