The perils and promises of fact-checking with large language models
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Fake news on Twitter during the 2016 U.S. presidential election
Grinberg, N., Joseph, K., Friedland, L., Swire-Thompson, B., & Lazer, D. (2019) · Science · doi:10.1126/science.aau2706 · Cited by 1,803
FEVER: a Large-scale Dataset for Fact Extraction and VERification
Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1074 · Cited by 1,343 · cited 2×
“For example, from encyclopedias (e.g., Wikipedia Thorne et al., 2018a), scientific papers (Wadden et al., 2020), or search engines such as Google (Augenstein et al., 2019).”
BackgroundBang, Y., Cahyawijaya, S., Lee, N., Dai, W., Su, D., Wilie, B., Lovenia, H., Ji, Z., Yu, T., Chung, W., et al. (2023) · Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.ijcnlp-main.45 · Cited by 682
ReAct: Synergizing Reasoning and Acting in Language Models
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.03629 · Cited by 608
A Survey on Automated Fact-Checking
Guo, Z., Schlichtkrull, M., & Vlachos, A. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00454 · Cited by 500 · cited 2×
“An assumption that (Guo et al., 2021) called unrealistic.”
BackgroundInvestigating the impact of user trust on the adoption and use of ChatGPT: Survey analysis
Choudhury, A., & Shamszare, H. (2023) · Journal of Medical Internet Research · doi:10.2196/47184 · Cited by 470 · cited 1×
“Instead, it may simply reflect the LLM’s retention of training examples.”
BackgroundBang, Y., Cahyawijaya, S., Lee, N., Dai, W., Su, D., Wilie, B., Lovenia, H., Ji, Z., Yu, T., Chung, W., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.04023 · Cited by 337
Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine
Jiao, W., Wang, W., Huang, J.-T., Wang, X., Shi, S., & Tu, Z. (2023) · arXiv · doi:10.48550/arxiv.2301.08745 · Cited by 317
The Fact Extraction and VERification (FEVER) Shared Task
Thorne, J., Vlachos, A., Cocarascu, O., Christodoulopoulos, C., & Mittal, A. (2018) · Proceedings of the First Workshop on Fact Extraction and VERification (FEVER) · doi:10.18653/v1/w18-5501 · Cited by 212 · cited 2×
“For example, from encyclopedias (e.g., Wikipedia Thorne et al., 2018a), scientific papers (Wadden et al., 2020), or search engines such as Google (Augenstein et al., 2019).”
BackgroundMethod
Cited by
Factuality challenges in the era of large language models and opportunities for fact-checking
Augenstein, I., Baldwin, T., Cha, M., Chakraborty, T., Ciampaglia, G. L., Corney, D., DiResta, R., Ferrara, E., Hale, S., Halevy, A., et al. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00881-z · Cited by 187
“Fact-checking is critical in information dissemination and modern journalism, and can benefit from the capabilities of LLMs in query phrasing, contextual information retrieval, explainability and reasoning, multilingual capabilities, summarization and so on 99 .”
The simulation of judgment in LLMs
Loru, E., Nudo, J., Di Marco, N., Santirocchi, A., Atzeni, R., Cinelli, M., Cestari, V., Rossi-Arnaud, C., & Quattrociocchi, W. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2518443122 · Cited by 57
Hallucination to truth: a review of fact-checking and factuality evaluation in large language models
Rahman, S. S., Islam, M. A., Alam, M. M., Zeba, M., Rahman, M. A., Chowa, S. S., Raiaan, M. A. K., & Azam, S. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-025-11454-w · Cited by 39
Sezgin, E., Jackson, D. I., Kocaballi, A. B., Bibart, M., Zupanec, S., Landier, W., Audino, A., Ranalli, M., & Skeens, M. (2025) · Cancer Medicine · doi:10.1002/cam4.70554 · Cited by 30
Content moderation by LLM: from accuracy to legitimacy
Huang, T. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11328-1 · Cited by 24
“Similar work of testing LLM’s ability in fact-checking has been done by ([89]).”
Background
Metadata
- Authors
- Quelle, D., & Bovet, A.
- Venue
- Frontiers in Artificial Intelligence
- Publisher
- Frontiers Media SA
- Published
- 2024-02-07
- Volume
- 7
- Pages
- 1341697-1341697
- ISSN
- 2624-8212 (ISSN-L)
- OpenAlex
- W4391610230
- Cited by
- 63
- References
- 11
- FWCI
- 46.25
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The perils and promises of fact-checking with large language models. https://app.cochat.ai/papers/10.3389/frai.2024.1341697
- The paper
- Quelle, D., & Bovet, A. (2024). The perils and promises of fact-checking with large language models. Frontiers in Artificial Intelligence. https://doi.org/10.3389/frai.2024.1341697
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.