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

arXiv: https://arxiv.org/abs/2306.07875 · HTML: https://mlsanity.com/paper/2306.07875/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 13 Jun 2023.

## Builds on (most cited first, 6 of 6)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Document Expansion by Query Prediction](https://mlsanity.com/paper/1904.08375/) (2019)
- [Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation](https://mlsanity.com/paper/2004.14503/) (2020)

## Built on by (most cited first, 3 of 3)

- [Evaluating Generative Ad Hoc Information Retrieval](https://mlsanity.com/paper/2311.04694/) (2023)
- [Iffy-Or-Not: Extending the Web to Support the Critical Evaluation of Fallacious Texts](https://mlsanity.com/paper/2503.14412/) (2025)
- [CoNewsReader: Supporting Comprehensive Understanding and Raising Critical Thoughts on Social Media News Through Comments](https://mlsanity.com/paper/2604.27905/) (2026)

## Abstract (arXiv)

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.