A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability
Year: 2025
Type: conference-paper
Abstract: In NLG meta-evaluation, evaluation metrics are typically assessed based on their consistency with humans.However, we identify some limitations in traditional NLG meta-evaluation approaches, such as issues in handling human ratings and ambiguous selections of correlation measures, which undermine the effectiveness of meta-evaluation.In this work, we propose a dual-perspective NLG meta-evaluation framework that focuses on different evaluation capabilities, thereby providing better interpretability.In addition, we introduce a method of automatically constructing the corresponding benchmarks without requiring new human annotations.Furthermore, we conduct experiments with 16 representative LLMs as the evaluators based on our proposed framework, comprehensively analyzing their evaluation performance from different perspectives.
Authors: Xinyu Hu, Mingqi Gao, Li Lin, Zhenghan Yu, Xiaojun Wan
Institution: Peking University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4412889840