Neurips_2026_acceptance

Our paper, “The Ruler and the Judge: Benchmark-Conditional Evaluation of LLM-as-a-Judge,” with Adrián Ghajari and Víctor Fresno, has been accepted to the NeurIPS 2026 Evaluations and Datasets Track! 🎉 The work examines how the quality of human benchmarks shapes the conclusions we can draw when evaluating LLM judges.