Web Retrieval Agents for Evidence-Based Misinformation Detection

Jacob-Junqi Tian, Hao Yu, Yury Orlovskiy, Tyler Vergho, Mauricio Rivera, Mayank Goel, Zachary Yang, Jean-François Godbout, Reihaneh Rabbany, Kellin Pelrine

Research Area: Safety, LMs and the world, LMs with tools and code

Keywords: Retrieval Augmented Generation, Information Retrieval, Misinformation Detection, LLM, Web-Browsing Agents

TL;DR: Pairing a strong LLM agent without internet access with a weaker one with access surpasses the performance of both agents in fact-checking and hallucination filtering.

Abstract: This paper develops an agent-based automated fact-checking approach for detecting misinformation. We demonstrate that combining a powerful LLM agent, which does not have access to the internet for searches, with an online web search agent yields better results than when each tool is used independently. Our approach is robust across multiple models, outperforming alternatives and increasing the macro F1 of misinformation detection by as much as 20 percent compared to LLMs without search. We also conduct extensive analyses on the sources our system leverages and their biases, decisions in the construction of the system like the search tool and the knowledge base, the type of evidence needed and its impact on the results, and other parts of the overall process. By combining strong performance with in-depth understanding, we hope to provide building blocks for future search-enabled misinformation mitigation systems.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 1008