Beyond Accuracy: Experts See AI Fact-Checks as Accurate but Less Useful

要旨

As misinformation proliferates online, large language models (LLMs) have been proposed as a promising tool to accelerate fact-checking workflows. While LLMs demonstrate strong performance in tasks such as text annotation, their capabilities in generating fact-checking reports remain uncertain. To investigate how media experts evaluate LLM-generated fact-checking reports, we conducted a 2 (Source: human vs. LLM) X 2 (Disclosure of Source: yes or no) between-subjects online experiment with media professionals (N=274). Our analyses reveal that experts perceive LLM-generated reports as significantly less useful than human-written reports; and such differences become larger when participants are not aware of the source. However, LLM-generated fact-checking reports were rated as accurate and logical as human-authored ones. Party affiliation plays a role in predicting perceived logicalness. Our findings advance the understanding of experts' evaluation of LLM-generated content within the context of misinformation, which provides important theoretical contributions to HCI and communication theories as well as practical implications for the field.

著者
Chenyan Jia
Northeastern University, Boston, Massachusetts, United States
Apoorva Gondimalla
University of Texas at Austin, Austin, Texas, United States
Angie Zhang
University of Texas at Austin, Austin, Texas, United States
David Joseph. Mullings
University of Texas at Austin, Austin, Texas, United States
Alexander Boltz
University of Washington, Seattle, Washington, United States
Min Kyung Lee
University of Texas at Austin, Austin, Texas, United States

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: Labor, Data and Ethics

P1 - Room 111
7 件の発表
2026-04-16 18:00:00
2026-04-16 19:30:00