Assessing the Reasoning Capabilities of LLMs in the context of Evidence-based Claim Verification

ACL ARR 2025 February Submission7786 Authors

Abstract: Although LLMs have shown great performance on Mathematics and Coding related reasoning tasks, the reasoning capabilities of LLMs regarding other forms of reasoning are still an open problem. Here, we examine the issue of reasoning from the perspective of claim verification. We propose a framework designed to break down any claim paired with evidence into atomic reasoning types that are necessary for verification. We use this framework to create RECV, the first claim verification benchmark, incorporating real-world claims, to assess the deductive and abductive reasoning capabilities of LLMs. The benchmark comprises of three datasets, covering reasoning problems of in creasing complexity. We evaluate three state of-the-art proprietary LLMs under multiple prompt settings. Our results show that while LLMs can address deductive reasoning prob lems, they consistently fail in cases of abductive reasoning. Moreover, we observe that enhancing LLMs with rationale generation is not always beneficial. Nonetheless, we find that generated rationales are semantically similar to those provided by humans, especially in deduc tive reasoning cases

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: Reasoning evaluation, LLM evaluation and benchmarking, Data resources, Claim verification and fact checking,

Contribution Types: Model analysis & interpretability, Data resources, Data analysis

Languages Studied: English

Submission Number: 7786