NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
46 results for “keyword:"sycophancy"” in ICLR 2027. 11 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability▼1.2k1.67
[PDF]Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments▼1.2k1.67
[PDF]If It Ain't Broke, Don't Fix It: Failures of Epistemic Control in Language-Model Agents▼4.3k2.00
[PDF]When Pleasing the User Compromises Care: AI Sycophancy in Caregiver-Mediated Healthcare▼4.3k2.00
[PDF]Diagnosing and Mitigating Sycophancy in LLMs via Attribution-Guided Activation Steering▼1.2k1.67
[PDF]TAKE THE HINT OR PUSH BACK? DECIDING WHEN A VISION-LANGUAGE MODEL SHOULD ACCEPT THE USER’S ANSWER▼1.2k3.00
[PDF]Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization▼5.8k2.33
[PDF]Evidence, Pressure, or Neither: What Actually Moves Costly Decisions in Large Language Models▲3.0k2.50
[PDF]Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories▲9.2k2.67
[PDF]They Know When They're Unsure: Confidence-Gated Acceptance as a Two-Sided Defense against Sycophancy in Video Language Models▼1.2k1.67
Withdrawn or desk rejected (11)
[PDF]Learning to Be Fooled: pretraining grows knowledge but keeps the scar of framing susceptibilityDesk rejected
[PDF]Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in LLMsWithdrawn1.67
[PDF]The Geometry of Sycophancy Breakdown: Dual-State Manifold Pathology and the Physical Limits of Representation SteeringWithdrawn1.33
[PDF]Mirroring Is Not Sycophancy: Style Convergence and Position Change in Human–AI ConversationWithdrawn1.67