# Paper Proposes Cross-Model Auditing to Harden LLM Judges Against Their Own Biases

Chain-of-Models routes a judgment through multiple models to identify the cognitive biases that prompt-based debiasing fails to fix.

- Published: 2026-08-03T05:38:34.576Z
- Canonical: https://polylog.news/ai/2026-08-03/paper-proposes-cross-model-auditing-to-harden-llm-judges-aga
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CL](https://arxiv.org/abs/2607.28636), [Anthropic Research](https://www.anthropic.com/research/team/societal-impacts)

Language models are increasingly used as automated judges, in evaluation harnesses, in reinforcement-learning reward signals, and in production content grading, but their verdicts inherit cognitive biases such as position and verbosity effe…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-03/paper-proposes-cross-model-auditing-to-harden-llm-judges-aga (subscription information: https://polylog.news/pricing).