Towards Unification of Hallucination Detection and Fact Verification for Large Language Models

TL;DR

This paper introduces UniFact, a unified framework for evaluating and comparing hallucination detection and fact verification in large language models, revealing their complementarity and proposing integrated approaches for improved factuality assessment.

Contribution

The paper presents UniFact, the first unified evaluation framework for hallucination detection and fact verification, facilitating direct comparison and integration of these paradigms in LLMs.

Findings

No single paradigm is universally best.

HD and FV capture different aspects of factual errors.

Hybrid methods outperform individual approaches.

Abstract

Large Language Models (LLMs) frequently exhibit hallucinations, generating content that appears fluent and coherent but is factually incorrect. Such errors undermine trust and hinder their adoption in real-world applications. To address this challenge, two distinct research paradigms have emerged: model-centric Hallucination Detection (HD) and text-centric Fact Verification (FV). Despite sharing the same goal, these paradigms have evolved in isolation, using distinct assumptions, datasets, and evaluation protocols. This separation has created a research schism that hinders their collective progress. In this work, we take a decisive step toward bridging this divide. We introduce UniFact, a unified evaluation framework that enables direct, instance-level comparison between FV and HD by dynamically generating model outputs and corresponding factuality labels. Through large-scale experiments across multiple LLM families and detection methods, we reveal three key findings: (1) No paradigm is universally superior; (2) HD and FV capture complementary facets of factual errors; and (3) hybrid approaches that integrate both methods consistently achieve state-of-the-art performance. Beyond benchmarking, we provide the first in-depth analysis of why FV and HD diverged, as well as empirical evidence supporting the need for their unification. The comprehensive experimental results call for a new, integrated research agenda toward unifying Hallucination Detection and Fact Verification in LLMs. We have open-sourced all the code, data, and baseline implementation at: https://github.com/oneal2000/UniFact/