Detecting and Controlling Sycophancy with Cascading Linear Features

Computer Science > Artificial Intelligence [Submitted on 23 Jun 2026] Detecting and Controlling Sycophancy with Cascading Linear Features Maty Bohacek, Rishub Jain, Nicholas Dufour, Thomas Leung, Chris Bregler, Roma Patel Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples that clearly exhibit desired or undesired behavior. These data pairs determine the degree to which interpretability frameworks can reliably detect model features responsible for a behavior, and therefore the ability to steer models toward or away from such behavior. In this work, we present an iterative data generation pipeline that isolates cascading linear features responsible for a behavior. Specifically, we show how moving beyond simple binary pairs of samples, and instead isolating samples that show degrees of features that scale linearly with behavior, allows for better disentanglement of features. We focus on detecting and steering away from sycophancy -- the tendency of language models to prioritize user validation. We demonstrate that sycophancy features discovered through cascading samples form linearly separable subspaces, and allow for selection of model activations that more clearly correspond to the desired behavior than baseline approaches. We also evaluate their ability to enable detection, deterministic scoring, and robust steering, and see that they either match or outperform LLM-as-a-judge and system prompting baselines while providing lower computational demand and more interpretability guarantees. Code & Data: this https URL Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.26155 [cs.AI]   (or arXiv:2606.26155v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.26155 Focus to learn more Submission history From: Maty Bohacek [view email] [v1] Tue, 23 Jun 2026 20:10:53 UTC (3,346 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark 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 Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)