@inproceedings{huang-etal-2026-meashalu,
    title = "{M}eas{H}alu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning",
    author = "Huang, Ruijun  and
      Kang, Zhiqiao  and
      Zhu, Yuxuan  and
      Li, Junxiong  and
      Zhao, Jiahao  and
      Tan, Minghuan  and
      Jiang, Feng  and
      Yang, Min",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1386/",
    pages = "27842--27859",
    ISBN = "979-8-89176-395-1",
    abstract = "The accurate extraction of scientific measurements from literature is a critical yet challenging task in AI4Science, enabling large-scale analysis and integration of quantitative research findings. However, Large Language Models (LLMs) frequently exhibit severe hallucinations, which significantly undermine the reliability of automated scientific document understanding systems. To address this problem, we propose MeasHalu, a novel framework for mitigating scientific measurement hallucinations through enhanced reasoning and targeted optimization. We first present a fine-grained taxonomy of measurement-specific hallucinations, categorizing errors across quantities, units, modifiers, and relations. Our approach incorporates a two-stage reasoning-aware fine-tuning strategy using augmented scientific data and process-based supervision. Furthermore, we introduce a progressive reward curriculum designed to penalize specific hallucination types, significantly improving extraction faithfulness. Experimental results demonstrate that MeasHalu substantially reduces hallucination rates and improves overall accuracy on the MeasEval benchmark. This work provides a targeted solution to a key bottleneck in automated scientific knowledge extraction, facilitating more trustworthy and scalable machine-assisted scientific literature analysis."
}