Fact-checking as a multi-step process: from ambiguity resolution to claim validation

Author

Wenbo Wang, New Jersey Institute of TechnologyFollow

Author ORCID Identifier

0000-0002-0784-7509

Document Type

Dissertation

Date of Award

5-31-2025

Degree Name

Doctor of Philosophy in Information Systems - (Ph.D.)

Department

Informatics

First Advisor

Yi-Fang Brook Wu

Second Advisor

Mark Cartwright

Third Advisor

Amy K. Hoover

Fourth Advisor

Hai Nhat Phan

Fifth Advisor

Xinyue Ye

Abstract

The spread of misinformation and disinformation has become a major concern, particularly with the rise of social media as a primary source of information for many people. Fact-checking—the process of verifying claims against credible evidence—has emerged as a critical safeguard against misinformation. Yet, the task is fraught with challenges: claims are often ambiguous, context-dependent, or composed of multiple intertwined assertions, while automated systems struggle to replicate the nuanced reasoning of human experts. This dissertation addresses these challenges by reimagining fact-checking as a multi-step, knowledge-guided process that systematically resolves ambiguity, decomposes complexity, and validates claims through structured reasoning. Additionally, the proposed frameworks integrate information retrieval and augmentation techniques to enhance claim verification. Information retrieval is employed to retrieve evidence from web sources, fact-checking databases, and structured knowledge graphs, ensuring comprehensive verification. Information augmentation leverage the retrieved evidence to provide contextual understanding, refine claim representations, and facilitate reasoning over retrieved information. Experimental results on multiple fact-checking datasets demonstrate that the proposed frameworks significantly improve accuracy compared to existing methods. This work contributes to the development of more scalable, interpretable, and context-aware fact-checking systems. A human-in-the-loop mechanism further enhances system reliability by handling ambiguous or unverifiable claims.

Recommended Citation

Wang, Wenbo, "Fact-checking as a multi-step process: from ambiguity resolution to claim validation" (2025). Dissertations. 1840.
https://digitalcommons.njit.edu/dissertations/1840