SOURCE-LINKED INTELLIGENCE

Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Large language models (LLMs) frequently exhibit \emph{sycophancy}: they adapt their answers to a user's stated beliefs or preferences instead of reporting what they hold to be true, which lowers factual accuracy and can amplify misinformation. This paper proposes a methodology for mitigating sycophancy that employs the Bayesian Truth Serum (BTS), a peer-prediction mechanism, as the reward in Group Relative Policy Optimization (GRPO) to fine-tune an LLM. BTS pays an answer for being \emph{surprisingly common}, that is, more frequent among respondents than those respondents themselves predicted.

Read original source ↗ Open in workspace

recordType

paper

region

Global