MeasHalu：通过增强推理缓解大型语言模型中的科学测量幻觉
MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning
AI总结：
本文提出MeasHalu框架，通过增强推理和针对性优化缓解LLM的科学测量幻觉问题，改进测量提取的准确性。
摘要：
科学文献中准确提取测量数据是AI4Science中的关键挑战，有助于大规模分析和整合定量研究结果。然而，大型语言模型（LLMs）经常表现出严重的幻觉，这显著削弱了自动化科学文档理解系统的可靠性。为了解决这个问题，我们提出了MeasHalu，一种通过增强推理和针对性优化来缓解科学测量幻觉的新框架。我们首先提出了一种细粒度的测量特定幻觉分类法，将误差分为数量、单位、修饰符和关系等方面。我们的方法结合了使用增强科学数据和基于过程的监督的两阶段推理感知微调策略。此外，我们引入了一种逐步奖励课程，旨在惩罚特定类型的幻觉，从而显著提高提取的忠实度。实验结果表明，MeasHalu显著降低了幻觉率，并在MeasEval基准上提高了整体准确性。这项工作为自动化科学知识提取中的关键瓶颈提供了有针对性的解决方案，促进了更可信和可扩展的机器辅助科学文献分析。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
