No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
arXiv:2609.17550 (cs)
[Submitted on 16 Jul 2026]
Title:No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback
View a PDF of the paper titled No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback, by Saad Aamir and Muhammad Awais Bin Adil
View PDF
HTML (experimental)
Abstract:Language models frequently abandon correct answers when users push back. We study this in two small instruction-tuned models from different families, Qwen2.5-1.5B and Llama-3.2-1B, over TriviaQA: the model answers, is challenged with one of four scripted pushback styles, and answers again. Conditioned on an initially correct answer, the models flip to a wrong answer in 41.8% and 43.1% of episodes. Which pressure works is a property of the model, not the pressure: the same within-question paired comparison (bare doubt vs. emotional appeal), specified in advance, is Bonferroni-significant in opposite directions across families (Qwen: bare doubt > emotional, OR 2.5, p=.040; Llama: emotional > bare doubt, OR 4.0, p=.001). Failure mode is also model-dependent: Llama abandons answers without recommitting at six times Qwen's rate (8.2% vs. 1.4%). Identical pushback repairs initially wrong answers only ~13% of the time; pushback is net epistemically destructive. We then ask whether capitulation is linearly decodable from the pre-response residual stream, a prerequisite for steering-vector interventions at that locus. A naive difference-in-means probe appears to succeed (in-sample AUROC 0.81/0.71), but a validation protocol combining question-level cross-validation, shuffled-label nulls, and a known-direction positive control shows the signal is overfitting: the best cross-validated AUROC is 0.582 in Qwen and 0.548 in Llama, both near or below their permutation thresholds and far under a pre-registered usability bar of 0.70, while the identical pipeline recovers a pushback-presence control direction at AUROC 1.000 in both. We further quantify a measurement hazard: substring grading underestimates capitulation by 18-24 percentage points. Code, prompts, transcripts, and analysis are released.
| Comments: | 12 pages, 3 figures. Code, transcripts, and analysis: this https URL |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2609.17550 [cs.CL] |
| (or arXiv:2609.17550v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.17550
arXiv-issued DOI via DataCite
|
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback, by Saad Aamir and Muhammad Awais Bin Adil
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
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 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
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
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
-
Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models
Oct 9
-
Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training
Oct 9
-
Language Models for Page-Level Layout Decisions in E-commerce Search
Oct 9
-
Measuring and Mitigating Solution Mode Collapse in RLVR
Oct 9
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.