The Perils & Promises of Fact-checking with Large Language Models

Abstract

Automated fact-checking, using machine learning to verify claims, has grown vital as misinformation spreads beyond human fact-checking capacity. Large Language Models (LLMs) like GPT-4 are increasingly trusted to write academic papers, lawsuits, and news articles and to verify information, emphasizing their role in discerning truth from falsehood and the importance of being able to verify their outputs. Understanding the capacities and limitations of LLMs in fact-checking tasks is therefore essential for ensuring the health of our information ecosystem. Here, we evaluate the use of LLM agents in fact-checking by having them phrase queries, retrieve contextual data, and make decisions. Importantly, in our framework, agents explain their reasoning and cite the relevant sources from the retrieved context. Our results show the enhanced prowess of LLMs when equipped with contextual information. GPT-4 outperforms GPT-3, but accuracy varies based on query language and claim veracity. While LLMs show promise in fact-checking, caution is essential due to inconsistent accuracy. Our investigation calls for further research, fostering a deeper comprehension of when agents succeed and when they fail.

References in corpus (12)

• Influence of fake news in Twitter during the 2016 US presidential election
• ReAct: Synergizing Reasoning and Acting in Language Models
• DeBERTa: Decoding-enhanced BERT with Disentangled Attention
• DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
• A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
• Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine
• Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases
• Shifting Polarization and Twitter News Influencers between two U.S. Presidential Elections
• The State of Human-centered NLP Technology for Fact-checking
• Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
• GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts
• News Verifiers Showdown: A Comparative Performance Evaluation of ChatGPT 3.5, ChatGPT 4.0, Bing AI, and Bard in News Fact-Checking

Cited by in corpus (5)

• Factuality Challenges in the Era of Large Language Models
• Fact-checking information from large language models can decrease headline discernment
• The simulation of judgment in LLMs
• Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models
• Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention