MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning

arXiv:2604.16929v1 Announce Type: new 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.

Related

• PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
• ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
• From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models
• InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis

Source: arXiv cs.CL | 2026-04-21