Swapping the Judge Changes the Ranking: A Preregistered Study of Cross-Provider Replication in LLM-Judged System Comparisons
cs.CL, cs.AI, cs.CY
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: 10 pages, 2 figures. Code and judge verdicts are provided as ancillary files
License: http://creativecommons.org/licenses/by/4.0/
The gist: Practitioners who compare systems with an LLM judge and have no human labels often check a conclusion by repeating it with a judge from another provider.
Abstract
Practitioners who compare systems with an LLM judge and have no human labels often check a conclusion by repeating it with a judge from another provider. We test how far that check can be trusted. In a preregistered study (with a disclosed post-registration reduction of the judge set), five judge models from three providers re-judged 4,000 Chatbot Arena battles (nine systems, 33 system pairs) that carry human votes, each in both response orders. Agreement with the human vote was low at the verdict level (median Cohen's kappa = 0.22), and system rankings did not survive a change of judge: Kendall's tau with the human ranking ranged from 0.17 to 0.89 (median 0.67), so the preregistered hypothesis that rankings remain stable was not supported. Conclusions replicated by two low-cost judges from different providers matched the human conclusion more often than single-judge conclusions (+0.10 precision), but the gain came from filtering out one poorly aligned judge, and replication involving that judge left a conclusion for only 35% of comparisons. Judges that agreed with humans reached a stable conclusion with no more verdicts than human votes required; the others failed to converge on 26-70% of system pairs at the sample sizes tested (up to 100 verdicts per pair). Disagreements with the human vote co-occurred across judges far more often than independence predicts, although a single human vote per battle cannot separate shared judge bias from voter noise.
Sources
- Who Judges Matters: Measuring Family-Conditioned Preference in LLM-as-Judge Panels
- Pair Difficulty Matters: Rethinking Pairwise LLM-as-a-Judge Evaluation and Consistency
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
- Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels
- LLM Evaluators Recognize and Favor Their Own Generations
- Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data