CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation

ArXi:2603.01865v2 Announce Type: replace LLM-as-judge evaluation has become standard practice for open-ended model assessment; however, judges exhibit systematic biases that cannot be eliminated 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. This work