FactCheck Editor: Multilingual Text Editor with End-to-End fact-checking

TL;DR

FactCheck Editor is a multilingual, end-to-end tool that automates fact-checking by detecting claims, retrieving evidence, and suggesting corrections, aiming to combat misinformation across 90+ languages.

Contribution

It introduces a comprehensive multilingual fact-checking workflow integrating claim detection, evidence retrieval, and correction suggestions using transformer models.

Findings

Effective claim detection across multiple languages

Accurate veracity prediction using NLI models

Successful evidence summarization and text revision suggestions

Abstract

We introduce 'FactCheck Editor', an advanced text editor designed to automate fact-checking and correct factual inaccuracies. Given the widespread issue of misinformation, often a result of unintentional mistakes by content creators, our tool aims to address this challenge. It supports over 90 languages and utilizes transformer models to assist humans in the labor-intensive process of fact verification. This demonstration showcases a complete workflow that detects text claims in need of verification, generates relevant search engine queries, and retrieves appropriate documents from the web. It employs Natural Language Inference (NLI) to predict the veracity of claims and uses LLMs to summarize the evidence and suggest textual revisions to correct any errors in the text. Additionally, the effectiveness of models used in claim detection and veracity assessment is evaluated across multiple languages.