conftrace_

sycophancy detection

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) dialogue system (2) model alignment (2) oversight reasoning (1) user behavior analysis (1) health information seeking (1) behavioral measurement (1) stance shift (1) assertion compliance (1) policy conflict (1)

Papers

Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling Agents EACL 2026 Trajectory Signatures of Deception in Large Language Models ACL 2026 Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent EMNLP 2025 Measuring Sycophancy of Language Models in Multi-turn Dialogues EMNLP 2025 “What’s Up, Doc?”: Analyzing How Users Seek Health Information in Large-Scale Conversational AI Datasets EMNLP 2025