BenHalluEval is the first dedicated hallucination benchmark for Bengali LLMs, using dual-track evaluation and the BenHalluScore metric to reveal variation in model calibration across seven LLMs.
In Find- ings of the Association for Computational Lin- guistics: ACL-IJCNLP 2021 , pages 4693–4703, Online
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali
BenHalluEval is the first dedicated hallucination benchmark for Bengali LLMs, using dual-track evaluation and the BenHalluScore metric to reveal variation in model calibration across seven LLMs.