LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric Validation
Lukáš Eigler Charles University Prague, Jindřich Libovický Charles University Prague, David Hurych Valeo.ai
Validating evaluation metrics for NLG typically relies on expensive and time-consuming human annotations, which predominantly exists only for English datasets. We propose LLM as a Meta-Judge, a scalable framework that utilizes LLMs to generate synthetic evaluation datasets via controlled semantic degradation of real data, replacing human judgment. We validate our approach using meta-correlation, measuring the alignment between metric rankings derived from synthetic data and those from standard human benchmarks. Experiments across Machine Translation, Question Answering, and Summarization demonstrate that synthetic validation serves as a reliable proxy for human judgment, achieving meta-correlations exceeding 0.9 in multilingual QA and proves to be a viable alternative where human judgments are unavailable or too expensive to obtain. Our code and data are publicly available at https://github.com/eiglerl/meta-judge.
尚无 AI 解读，展示原文摘要
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) · 2026 · 正式发表