Debunk Lists as External Knowledge Structures for Health Misinformation Detection with Generative AI

The rapid dissemination of health misinformation on the Internet and social media has become a growing challenge for public health, particularly in terms of health information credibility. Promising efforts have been made to detect misinformation using generative AI and large language models (LLMs). However, such tools still lack domain-specific knowledge that limits their performance. In this study, we examine the use of predefined knowledge data structures in the forms of debunk lists to augment existing LLMs’ capabilities. We evaluate five different LLMs, including Llama-3.1-8B-instruct, Mistral-large, GPT-4o-mini, Claude-3.5-haiku, and Gemini-1.5-flash, under three experimental settings: zero-shot and debunk-augmented (50 and 100 entities). Results show that external knowledge, in the form of debunk lists, can notably improve LLMs’ performance in detecting misinformation. While Llama shows minimal benefit, the F1 score improvement ranges from 2.63% (GPT-4o) to 11% (Claude). In addition, analysis of model justifications shows that frequent use of debunk lists does not necessarily relate to accurate predictions. This highlights the importance of a model’s ability in effectively using the debunk list rather than reporting superficial integration of external knowledge. Moreover, the proposed framework is generalizable to other misinformation domains and provides key insights for applying external knowledge and evaluating LLMs’ reasoning reliability.