ReadProbe: A Demo of Retrieval-Enhanced Large Language Models to Support Lateral Reading
This addresses the issue of misinformation for general users by providing a tool to enhance credibility evaluation, though it appears incremental as it combines existing technologies like LLMs and search engines.
The paper tackles the problem of online misinformation by developing ReadProbe, a tool that uses retrieval-enhanced large language models to support lateral reading, resulting in a web-based application that helps reduce the risk of being misled by false information and won first prize in a national AI misinformation hackathon.
With the rapid growth and spread of online misinformation, people need tools to help them evaluate the credibility and accuracy of online information. Lateral reading, a strategy that involves cross-referencing information with multiple sources, may be an effective approach to achieving this goal. In this paper, we present ReadProbe, a tool to support lateral reading, powered by generative large language models from OpenAI and the Bing search engine. Our tool is able to generate useful questions for lateral reading, scour the web for relevant documents, and generate well-attributed answers to help people better evaluate online information. We made a web-based application to demonstrate how ReadProbe can help reduce the risk of being misled by false information. The code is available at https://github.com/DakeZhang1998/ReadProbe. An earlier version of our tool won the first prize in a national AI misinformation hackathon.