Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Experts

TL;DR

This paper introduces a novel methodology using large language models to assess the factuality and political bias of news outlets by emulating professional fact-checkers' criteria, with extensive experiments and dataset release.

Contribution

It proposes a new LLM-based approach for profiling news media outlets' reliability and bias, focusing on entire sources rather than individual claims, and provides a comprehensive dataset and analysis.

Findings

LLMs outperform strong baselines in media profiling tasks

Media popularity and region influence model performance

Key dataset components identified through ablation study

Abstract

In an age characterized by the proliferation of mis- and disinformation online, it is critical to empower readers to understand the content they are reading. Important efforts in this direction rely on manual or automatic fact-checking, which can be challenging for emerging claims with limited information. Such scenarios can be handled by assessing the reliability and the political bias of the source of the claim, i.e., characterizing entire news outlets rather than individual claims or articles. This is an important but understudied research direction. While prior work has looked into linguistic and social contexts, we do not analyze individual articles or information in social media. Instead, we propose a novel methodology that emulates the criteria that professional fact-checkers use to assess the factuality and political bias of an entire outlet. Specifically, we design a variety of prompts based on these criteria and elicit responses from large language models (LLMs), which we aggregate to make predictions. In addition to demonstrating sizable improvements over strong baselines via extensive experiments with multiple LLMs, we provide an in-depth error analysis of the effect of media popularity and region on model performance. Further, we conduct an ablation study to highlight the key components of our dataset that contribute to these improvements. To facilitate future research, we released our dataset and code at https://github.com/mbzuai-nlp/llm-media-profiling.