04:00
2026-08-03
arxiv.org
artificial-intelligence
Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges
A new arXiv preprint (2607.28636v1) introduces Chain-of-Models (CoM), an automated audit pipeline in which a second model inspects a first model's reasoning trace to reduce cognitive biases in LLM judโฆ