Overview

Claim verification checks statements against documents, databases, tables, images, audio, or other evidence, supporting fact-checking, scientific review, and safer AI-generated answers. Common systems retrieve and rank evidence, break complex statements into smaller claims, then apply natural language inference, language-model reasoning, or structured calculations to judge support, contradiction, or insufficient evidence. Current approaches also use multiple sources or agents, explicit evidence traces, calibration, and abstention to handle conflicts and limit cost or risk. A central challenge is ensuring that benchmark gains reflect robust reasoning rather than dataset shortcuts, while deciding how much evidence is sufficient and when a system should defer to people.

Latest papers

CardsList

63 papers5 papers in the last four weeks, down 44% on the four weeks before. 0.0% of all new papers.

  1. Analyzing LLM Instruction Optimization for Tabular Fact Verification

    Feb 20, 2026Xiaotang Du, Giwon Hong, Wai-Chung Kwan +4Prompt OptimizationLarge Language Model-Guided Optimization

  2. Human-AI Complementarity: A Goal for Amplified Oversight

    Oct 30, 2025Rishub Jain, Sophie Bridgers, Lili Janzer +3Human-AI ComplementarityClaim Verification