ReadProbe: A Demo of Retrieval-Enhanced Large Language Models to Support Lateral Reading

TL;DR

ReadProbe is a web-based tool that leverages large language models and search engines to facilitate lateral reading, helping users evaluate online information's credibility by generating questions, sourcing relevant documents, and providing attributed answers.

Contribution

This paper introduces ReadProbe, a novel tool that integrates generative language models and search engines to support lateral reading for misinformation detection.

Findings

ReadProbe effectively generates questions for lateral reading.

The tool can scour the web for relevant documents.

It provides well-attributed answers to aid credibility assessment.

Abstract

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.