Table-Text Alignment: Explaining Claim Verification Against Tables in Scientific Papers
Scientific claim verification against tables typically requires predicting whether a claim is supported or refuted given a table. However, we argue that predicting the final label alone is insufficient: it reveals little about the model's reasoning and offers limited interpretability. To address this, we reframe table-text alignment as an explanation task, requiring models to identify the table cells essential for claim verification. We build a new dataset by extending the SciTab benchmark with human-annotated cell-level rationales. Annotators verify the claim label and highlight the minimal set of cells needed to support their decision. After the annotation process, we utilize the collected information and propose a taxonomy for handling ambiguous cases. Our experiments show that (i) incorporating table alignment information improves claim verification performance, and (ii) most LLMs, while often predicting correct labels, fail to recover human-aligned rationales, suggesting that their predictions do not stem from faithful reasoning.
Code (1)
Tasks
Claim VerificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Enoki: Efficient Multi-Level Hallucination Detection
Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existing hallucination detectors usually operate at a single level: claim-level methods provide interpretable factual units, wh…
Open Information ExtractionAVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web
Existing datasets for automated fact-checking have substantial limitations, such as relying on artificial claims, lacking annotations for evidence and intermediate reasoning, or including evidence published after the cla…
Claim VerificationFact CheckingQuestion AnsweringFactLens: Benchmarking Fine-Grained Fact Verification
Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation. To verify LL…
BenchmarkingFact VerificationText GenerationDistill and Align Decomposition for Enhanced Claim Verification
Complex claim verification requires decomposing sentences into verifiable subclaims, yet existing methods struggle to align decomposition quality with verification performance. We propose a reinforcement learning (RL) ap…
Reinforcement LearningDeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation
Misalignment between claims and their cited evidence is a common failure mode in reports generated by large language models, limiting their reliability in scientific and other high-stakes settings. We present DeepSciVeri…
Text Retrieval