A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918125394460672 |
|---|---|
| author | Hu, Xinyu Gao, Mingqi Lin, Li Yu, Zhenghan Wan, Xiaojun |
| author_facet | Hu, Xinyu Gao, Mingqi Lin, Li Yu, Zhenghan Wan, Xiaojun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12052 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability Hu, Xinyu Gao, Mingqi Lin, Li Yu, Zhenghan Wan, Xiaojun Computation and Language 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. |
| title | A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.12052 |