InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs

2026-01-10

arXiv.org

AI Summary

This work addresses the limitations of existing fact-checking approaches for large language models, which are often confined to binary classification, lack interpretability, and fail to identify fine-grained error types. To overcome these challenges, the authors propose InFi-Checker, the first interpretable and fine-grained fact-checking framework. It leverages a controlled data synthesis pipeline to construct InFi-Check-FG, a high-quality dataset annotated with explicit evidence, fine-grained error labels, natural-language rationales, and corrected statements. Built upon this dataset, the multi-task InFi-Checker model jointly predicts evidence, error categories, explanations, and corrections. The model achieves state-of-the-art performance on InFi-Check-FG and demonstrates strong generalization across diverse downstream tasks, significantly enhancing the practicality and trustworthiness of automated fact-checking.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Large language models (LLMs) often hallucinate, yet most existing fact-checking methods treat factuality evaluation as a binary classification problem, offering limited interpretability and failing to capture fine-grained error types. In this paper, we introduce InFi-Check, a framework for interpretable and fine-grained fact-checking of LLM outputs. Specifically, we first propose a controlled data synthesis pipeline that generates high-quality data featuring explicit evidence, fine-grained error type labels, justifications, and corrections. Based on this, we further construct large-scale training data and a manually verified benchmark InFi-Check-FG for fine-grained fact-checking of LLM outputs. Building on these high-quality training data, we further propose InFi-Checker, which can jointly provide supporting evidence, classify fine-grained error types, and produce justifications along with corrections. Experiments show that InFi-Checker achieves state-of-the-art performance on InFi-Check-FG and strong generalization across various downstream tasks, significantly improving the utility and trustworthiness of factuality evaluation.

Problem

• fact-checking
• hallucination
• fine-grained error
• interpretability
• large language models

Innovation

• fine-grained fact-checking
• interpretable AI
• controlled data synthesis
• LLM hallucination
• evidence-based correction