OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511599" target="_blank" >RIV/00216208:11320/25:10511599 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2025.inlg-main.19" target="_blank" >https://aclanthology.org/2025.inlg-main.19</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs

Popis výsledku v původním jazyce

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. We introduce OpeNLGauge, a fully open-source, reference-free NLG evaluation metric that provides accurate explanations based on individual 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.

Název v anglickém jazyce

OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs

Popis výsledku anglicky

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. We introduce OpeNLGauge, a fully open-source, reference-free NLG evaluation metric that provides accurate explanations based on individual 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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 18th International Natural Language Generation Conference

ISBN

979-8-89176-321-0

ISSN

—

e-ISSN

—

Počet stran výsledku

46

Strana od-do

292-337

Název nakladatele

Association for Computational Linguistics

Místo vydání

Kerrville, TX, USA

Místo konání akce

Hanoi, Vietnam

Datum konání akce

29. 10. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—