OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909909947252736 |
|---|---|
| author | Kartáč, Ivan Lango, Mateusz Dušek, Ondřej |
| author_facet | Kartáč, Ivan Lango, Mateusz Dušek, Ondřej |
| contents | Large Language Models (LLMs) have demonstrated great potential as evaluators of NLG systems, allowing for high-quality, reference-free, and multi-aspect assessments. However, existing LLM-based metrics suffer from two major drawbacks: reliance on proprietary models to generate training data or perform evaluations, and a lack of fine-grained, explanatory feedback. In this paper, we introduce OpeNLGauge, a fully open-source, reference-free NLG evaluation metric that provides accurate explanations based on error spans. OpeNLGauge is available as a two-stage ensemble of larger open-weight LLMs, or as a small fine-tuned evaluation model, with confirmed generalizability to unseen tasks, domains and aspects. Our extensive meta-evaluation shows that OpeNLGauge achieves competitive correlation with human judgments, outperforming state-of-the-art models on certain tasks while maintaining full reproducibility and providing explanations more than twice as accurate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11858 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs Kartáč, Ivan Lango, Mateusz Dušek, Ondřej Computation and Language Large Language Models (LLMs) have demonstrated great potential as evaluators of NLG systems, allowing for high-quality, reference-free, and multi-aspect assessments. However, existing LLM-based metrics suffer from two major drawbacks: reliance on proprietary models to generate training data or perform evaluations, and a lack of fine-grained, explanatory feedback. In this paper, we introduce OpeNLGauge, a fully open-source, reference-free NLG evaluation metric that provides accurate explanations based on error spans. OpeNLGauge is available as a two-stage ensemble of larger open-weight LLMs, or as a small fine-tuned evaluation model, with confirmed generalizability to unseen tasks, domains and aspects. Our extensive meta-evaluation shows that OpeNLGauge achieves competitive correlation with human judgments, outperforming state-of-the-art models on certain tasks while maintaining full reproducibility and providing explanations more than twice as accurate. |
| title | OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.11858 |