FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lin, Hongzhan, Deng, Yang, Gu, Yuxuan, Zhang, Wenxuan, Ma, Jing, Ng, See-Kiong, Chua, Tat-Seng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913714025791488
author Lin, Hongzhan
Deng, Yang
Gu, Yuxuan
Zhang, Wenxuan
Ma, Jing
Ng, See-Kiong
Chua, Tat-Seng
author_facet Lin, Hongzhan
Deng, Yang
Gu, Yuxuan
Zhang, Wenxuan
Ma, Jing
Ng, See-Kiong
Chua, Tat-Seng
contents Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the justification production and uncover the nuanced limitations of LLMs in fact-checking. In this work, we introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities. Leveraging importance sampling principles and multi-agent collaboration, FACT-AUDIT generates adaptive and scalable datasets, performs iterative model-centric evaluations, and updates assessments based on model-specific responses. By incorporating justification production alongside verdict prediction, this framework provides a comprehensive and evolving audit of LLMs' factual reasoning capabilities, to investigate their trustworthiness. Extensive experiments demonstrate that FACT-AUDIT effectively differentiates among state-of-the-art LLMs, providing valuable insights into model strengths and limitations in model-centric fact-checking analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models
Lin, Hongzhan
Deng, Yang
Gu, Yuxuan
Zhang, Wenxuan
Ma, Jing
Ng, See-Kiong
Chua, Tat-Seng
Computation and Language
Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the justification production and uncover the nuanced limitations of LLMs in fact-checking. In this work, we introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities. Leveraging importance sampling principles and multi-agent collaboration, FACT-AUDIT generates adaptive and scalable datasets, performs iterative model-centric evaluations, and updates assessments based on model-specific responses. By incorporating justification production alongside verdict prediction, this framework provides a comprehensive and evolving audit of LLMs' factual reasoning capabilities, to investigate their trustworthiness. Extensive experiments demonstrate that FACT-AUDIT effectively differentiates among state-of-the-art LLMs, providing valuable insights into model strengths and limitations in model-centric fact-checking analysis.
title FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2502.17924