conftrace_

oversight reasoning

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

sycophancy detection (1) large language model (1) human-ai interaction (1) bias mitigation (1) model alignment (1) ai safety (1) model safety (1)

Papers

Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent EMNLP 2025