# CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation

arXiv: https://arxiv.org/abs/2603.01865 · HTML: https://mlsanity.com/paper/2603.01865/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 15 of 15)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [tinyBenchmarks: evaluating LLMs with fewer examples](https://mlsanity.com/paper/2402.14992/) (2024)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations](https://mlsanity.com/paper/2411.00640/) (2024)
- [Can You Trust LLM Judgments? Reliability of LLM-as-a-Judge](https://mlsanity.com/paper/2412.12509/) (2024)
- [Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data](https://mlsanity.com/paper/2410.13341/) (2024)
- [Do Repetitions Matter? Strengthening Reliability in LLM Evaluations](https://mlsanity.com/paper/2509.24086/) (2025)
- [Beyond the Singular: Revealing the Value of Multiple Generations in Benchmark Evaluation](https://mlsanity.com/paper/2502.08943/) (2025)
- [LLM-as-Judge on a Budget](https://mlsanity.com/paper/2602.15481/) (2026)

## Built on by (most cited first, 4 of 4)

- [When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels](https://mlsanity.com/paper/2605.06652/) (2026)
- [AI Rater Discrimination Depends on Scoring Protocol in Complex Clinical Decision-Making](https://mlsanity.com/paper/2606.03198/) (2026)
- [Optimizing Sparse Outcomes Through Dense Behavioral Signals via Value-Guided Preference Distillation](https://mlsanity.com/paper/2609.14648/) (2026)
- [False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift](https://mlsanity.com/paper/2610.01535/) (2026)

## Abstract (arXiv)

LLM-as-judge evaluation has become standard practice for open-ended model assessment; however, judges exhibit systematic biases that cannot be averaged out by increasing the number of scenarios or generations. These biases are often similar in magnitude to the model differences that benchmarks are designed to detect, resulting in unreliable rankings when single-judge evaluations are used. We introduce a variance decomposition that partitions benchmark score variance into scenario, generation, judge, and residual components. Based on this analysis, CyclicJudge, a round-robin assignment of judges to scenarios, is demonstrated to be the optimal strategy for a fixed judge panel and judge-call budget: the score recovers the panel mean exactly while matching the cost of single-judge evaluation. Empirical results on MT-Bench and MindEval validate the effectiveness of CyclicJudge as predicted, across both general-purpose and domain-specific evaluation settings.