Web Retrieval Agents for Evidence-Based Misinformation Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Jacob-Junqi, Yu, Hao, Orlovskiy, Yury, Vergho, Tyler, Rivera, Mauricio, Goel, Mayank, Yang, Zachary, Godbout, Jean-Francois, Rabbany, Reihaneh, Pelrine, Kellin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916430813855744
author Tian, Jacob-Junqi
Yu, Hao
Orlovskiy, Yury
Vergho, Tyler
Rivera, Mauricio
Goel, Mayank
Yang, Zachary
Godbout, Jean-Francois
Rabbany, Reihaneh
Pelrine, Kellin
author_facet Tian, Jacob-Junqi
Yu, Hao
Orlovskiy, Yury
Vergho, Tyler
Rivera, Mauricio
Goel, Mayank
Yang, Zachary
Godbout, Jean-Francois
Rabbany, Reihaneh
Pelrine, Kellin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_00009
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Web Retrieval Agents for Evidence-Based Misinformation Detection
Tian, Jacob-Junqi
Yu, Hao
Orlovskiy, Yury
Vergho, Tyler
Rivera, Mauricio
Goel, Mayank
Yang, Zachary
Godbout, Jean-Francois
Rabbany, Reihaneh
Pelrine, Kellin
Information Retrieval
Artificial Intelligence
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.
title Web Retrieval Agents for Evidence-Based Misinformation Detection
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2409.00009