MUCH: A Multilingual Claim Hallucination Benchmark

Jérémie Dentan, Alexi Stanislas Canesse, Davide Buscaldi, Aymen Shabou, Sonia Vanier


Abstract
Claim-level Uncertainty Quantification (UQ) is a promising approach to mitigate the lack of reliability in Large Language Models (LLMs). We introduce MUCH, the first claim-level UQ benchmark designed for fair and reproducible evaluation of future methods under realistic conditions. It includes 4,876 samples across four European languages (English, French, Spanish, and German) and four instruction-tuned open-weight LLMs. Unlike prior claim-level benchmarks, we release 24 generation logits per token, facilitating the development of future white-box methods without re-generating data. Moreover, in contrast to previous benchmarks that rely on manual or LLM-based segmentation, we propose a new deterministic algorithm capable of segmenting claims using as little as 0.1% of the LLM generation time. This makes our segmentation approach suitable for real-time monitoring of LLM outputs, ensuring that MUCH evaluates UQ methods under realistic deployment constraints. Finally, our evaluations show that current methods still have substantial room for improvement in both performance and efficiency.
Anthology ID:
2026.lrec-1.176
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
2249–2267
Language:
External URL:
https://lrec.elra.info/lrec2026-main-176
DOI:
10.63317/4zrfhra4azck
Bibkey:
Cite (ACL):
Jérémie Dentan, Alexi Stanislas Canesse, Davide Buscaldi, Aymen Shabou, and Sonia Vanier. 2026. MUCH: A Multilingual Claim Hallucination Benchmark. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2249–2267, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
MUCH: A Multilingual Claim Hallucination Benchmark (Dentan et al., LREC 2026)
Copy Citation: