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

arXiv: https://arxiv.org/abs/2310.13549 · HTML: https://mlsanity.com/paper/2310.13549/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 59 references that are in the map.
- First posted on arXiv 20 Oct 2023.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine](https://mlsanity.com/paper/2301.08745/) (2023)
- [MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims](https://mlsanity.com/paper/1909.03242/) (2019)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [The Fact Extraction and VERification (FEVER) Shared Task](https://mlsanity.com/paper/1811.10971/) (2018)
- [Explainable Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2011.03870/) (2020)
- [That is a Known Lie: Detecting Previously Fact-Checked Claims](https://mlsanity.com/paper/2005.06058/) (2020)
- [RumourEval 2019: Determining Rumour Veracity and Support for Rumours](https://mlsanity.com/paper/1809.06683/) (2018)
- [Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases](https://mlsanity.com/paper/2009.11564/) (2020)
- [Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2109.11427/) (2021)
- [Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation](https://mlsanity.com/paper/2310.09223/) (2023)
- [News Verifiers Showdown: A Comparative Performance Evaluation of ChatGPT 3.5, ChatGPT 4.0, Bing AI, and Bard in News Fact-Checking](https://mlsanity.com/paper/2306.17176/) (2023)
- [Matching Tweets With Applicable Fact-Checks Across Languages](https://mlsanity.com/paper/2202.07094/) (2022)
- [Shifting Polarization and Twitter News Influencers between two U.S. Presidential Elections](https://mlsanity.com/paper/2111.02505/) (2021)

## Built on by (most cited first, 30 of 31)

- [Content Moderation by LLM: From Accuracy to Legitimacy](https://mlsanity.com/paper/2409.03219/) (2024)
- [Claim Verification in the Age of Large Language Models: A Survey](https://mlsanity.com/paper/2408.14317/) (2024)
- [Multi-Agent Debate for LLM Judges with Adaptive Stability Detection](https://mlsanity.com/paper/2510.12697/) (2025)
- [The simulation of judgment in LLMs](https://mlsanity.com/paper/2502.04426/) (2025)
- [Logical Consistency of Large Language Models in Fact-checking](https://mlsanity.com/paper/2412.16100/) (2024)
- [Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models](https://mlsanity.com/paper/2508.03860/) (2025)
- [Challenges for Generative AI in Legal Reasoning](https://mlsanity.com/paper/2508.18880/) (2025)
- [Evaluating open-source Large Language Models for automated fact-checking](https://mlsanity.com/paper/2503.05565/) (2025)
- [Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation](https://mlsanity.com/paper/2506.07211/) (2025)
- [MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs](https://mlsanity.com/paper/2510.22967/) (2025)
- [Look It Up: Analysing Internal Web Search Capabilities of Modern LLMs](https://mlsanity.com/paper/2511.18931/) (2025)
- [VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference](https://mlsanity.com/paper/2512.18853/) (2025)
- [Fact-checking with Generative AI: A Systematic Cross-Topic Examination of LLMs Capacity to Detect Veracity of Political Information](https://mlsanity.com/paper/2503.08404/) (2025)
- [Relative Bias: A Comparative Framework for Quantifying Bias in LLMs](https://mlsanity.com/paper/2505.17131/) (2025)
- [Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine](https://mlsanity.com/paper/2506.20876/) (2025)
- [ConsistencyAI: A Benchmark to Assess LLMs' Factual Consistency When Responding to Different Demographic Groups](https://mlsanity.com/paper/2510.13852/) (2025)
- [Generative Debunking of Climate Misinformation](https://mlsanity.com/paper/2407.05599/) (2024)
- [A Comparative Study of Translation Bias and Accuracy in Multilingual Large Language Models for Cross-Language Claim Verification](https://mlsanity.com/paper/2410.10303/) (2024)
- [On Fact and Frequency: LLM Responses to Misinformation Expressed with Uncertainty](https://mlsanity.com/paper/2503.04271/) (2025)
- [Iffy-Or-Not: Extending the Web to Support the Critical Evaluation of Fallacious Texts](https://mlsanity.com/paper/2503.14412/) (2025)
- [Effective Yet Ephemeral Propaganda Defense: There Needs to Be More than One-Shot Inoculation to Enhance Critical Thinking](https://mlsanity.com/paper/2503.16497/) (2025)
- [Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks](https://mlsanity.com/paper/2510.08605/) (2025)
- [Understanding Critical Thinking in Generative Artificial Intelligence Use: Development, Validation, and Correlates of the Critical Thinking in AI Use Scale](https://mlsanity.com/paper/2512.12413/) (2025)
- [Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation](https://mlsanity.com/paper/2512.16189/) (2025)
- [Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs](https://mlsanity.com/paper/2604.04177/) (2026)
- [Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs](https://mlsanity.com/paper/2606.08605/) (2026)
- [Understanding Inequality of LLM Fact-Checking over Geographic Regions with Agent and Retrieval models](https://mlsanity.com/paper/2503.22877/) (2025)
- [From prosthetic memory to prosthetic denial: Auditing whether large language models are prone to mass atrocity denialism](https://mlsanity.com/paper/2505.21753/) (2025)
- [MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment](https://mlsanity.com/paper/2601.22361/) (2026)
- [The Alignment Bottleneck in Decomposition-Based Claim Verification](https://mlsanity.com/paper/2602.10380/) (2026)

## Abstract (arXiv)

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.