HRDE: Retrieval-Augmented Large Language Models for Chinese Health Rumor Detection and Explainability
This addresses the threat of health misinformation to public health in China by providing a scalable detection and explanation tool, though it is incremental as it builds on existing retrieval-augmented LLM methods.
The paper tackled the problem of detecting false health information (rumors) in Chinese by constructing HealthRCN, a dataset of 1.12 million health-related rumors, and proposed HRDE, a retrieval-augmented large language model that achieved an average accuracy of 91.04% and F1 score of 91.58%, outperforming models like GPT-4-1106-Preview.
As people increasingly prioritize their health, the speed and breadth of health information dissemination on the internet have also grown. At the same time, the presence of false health information (health rumors) intermingled with genuine content poses a significant potential threat to public health. However, current research on Chinese health rumors still lacks a large-scale, public, and open-source dataset of health rumor information, as well as effective and reliable rumor detection methods. This paper addresses this gap by constructing a dataset containing 1.12 million health-related rumors (HealthRCN) through web scraping of common health-related questions and a series of data processing steps. HealthRCN is the largest known dataset of Chinese health information rumors to date. Based on this dataset, we propose retrieval-augmented large language models for Chinese health rumor detection and explainability (HRDE). This model leverages retrieved relevant information to accurately determine whether the input health information is a rumor and provides explanatory responses, effectively aiding users in verifying the authenticity of health information. In evaluation experiments, we compared multiple models and found that HRDE outperformed them all, including GPT-4-1106-Preview, in rumor detection accuracy and answer quality. HRDE achieved an average accuracy of 91.04% and an F1 score of 91.58%.