Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim $\rightarrow$ Evidence Reasoning

TL;DR

This paper introduces CLAIM-BENCH, a benchmark for assessing large language models' ability to understand and validate scientific claims and evidence, revealing current limitations and strengths across different models and prompting strategies.

Contribution

The study presents CLAIM-BENCH, a novel benchmark for scientific claim-evidence reasoning in LLMs, and systematically evaluates multiple models and approaches, highlighting their capabilities and shortcomings.

Findings

GPT-4 and Claude outperform open-source models in accuracy.

Three-pass and one-by-one prompting improve claim-evidence linking.

Significant limitations remain in LLMs' understanding of complex scientific content.

Abstract

Large language models (LLMs) are increasingly being used for complex research tasks such as literature review, idea generation, and scientific paper analysis, yet their ability to truly understand and process the intricate relationships within complex research papers, such as the logical links between claims and supporting evidence remains largely unexplored. In this study, we present CLAIM-BENCH, a comprehensive benchmark for evaluating LLMs' capabilities in scientific claim-evidence extraction and validation, a task that reflects deeper comprehension of scientific argumentation. We systematically compare three approaches which are inspired by divide and conquer approaches, across six diverse LLMs, highlighting model-specific strengths and weaknesses in scientific comprehension. Through evaluation involving over 300 claim-evidence pairs across multiple research domains, we reveal significant limitations in LLMs' ability to process complex scientific content. Our results demonstrate that closed-source models like GPT-4 and Claude consistently outperform open-source counterparts in precision and recall across claim-evidence identification tasks. Furthermore, strategically designed three-pass and one-by-one prompting approaches significantly improve LLMs' abilities to accurately link dispersed evidence with claims, although this comes at increased computational cost. CLAIM-BENCH sets a new standard for evaluating scientific comprehension in LLMs, offering both a diagnostic tool and a path forward for building systems capable of deeper, more reliable reasoning across full-length papers.