Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
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)
|
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
Current browse context:
References & Citations
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
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.
More from arXiv — NLP / Computation & Language
-
EDEN: A Large-Scale Corpus of Clinical Notes for Italian
Jun 12
-
Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures
Jun 12
-
MARD: Mirror-Augmented Reasoning Distillation for Mechanism-Level Drug-Drug Interaction Prediction
Jun 12
-
Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation
Jun 12
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.