mlsanityData to 7 Oct 2026

Language Models as Fact Checkers?

arXiv 2006.04102 ↗First posted 7 Jun 2020cs.CL cs.AIcited by 51

Not on the map. Why?

Abstract (arXiv)

Recent work has suggested that language models (LMs) store both common-sense and factual knowledge learned from pre-training data. In this paper, we leverage this implicit knowledge to create an effective end-to-end fact checker using a solely a language model, without any external knowledge or explicit retrieval components. While previous work on extracting knowledge from LMs have focused on the task of open-domain question answering, to the best of our knowledge, this is the first work to examine the use of language models as fact checkers. In a closed-book setting, we show that our zero-shot LM approach outperforms a random baseline on the standard FEVER task, and that our fine-tuned LM compares favorably with standard baselines. Though we do not ultimately outperform methods which use explicit knowledge bases, we believe our exploration shows that this method is viable and has much room for exploration.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 12; 2023: 10; 2024: 8; 2025: 6; 2026: 4.

51 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2021Editing Factual Knowledge in Language Modelscited by 548
  3. 2021A Survey on Automated Fact-Checkingcited by 376
  4. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 290
  5. 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
  6. 2021Automated Fact-Checking for Assisting Human Fact-Checkerscited by 144
  7. 2023Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Methodcited by 97
  8. 2022Calibrating Factual Knowledge in Pretrained Language Modelscited by 92
  9. 2021A Survey on Stance Detection for Mis- and Disinformation Identificationcited by 75
  10. 2022Iteratively Prompt Pre-trained Language Models for Chain of Thoughtcited by 75
  11. 2021Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resourcescited by 71
  12. 2021Towards Few-Shot Fact-Checking via Perplexitycited by 63
38 more
  1. 2021GooAQ: Open Question Answering with Diverse Answer Typescited by 53
  2. 2022Synthetic Disinformation Attacks on Automated Fact Verification Systemscited by 44
  3. 2022CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweetscited by 29
  4. 2022NeuS: Neutral Multi-News Summarization for Mitigating Framing Biascited by 26
  5. 2023On the application of Large Language Models for language teaching and assessment technologycited by 26
  6. 2024Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verificationcited by 17
  7. 2024Tracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledgecited by 14
  8. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Modelscited by 13
  9. 2023Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Modelscited by 11
  10. 2024ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphscited by 11
  11. 2024More Victories, Less Cooperation: Assessing Cicero's Diplomacy Playcited by 9
  12. 2022Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweetscited by 7
  13. 2022Autonomation, Not Automation: Activities and Needs of European Fact-checkers as a Basis for Designing Human-Centered AI Systemscited by 7
  14. 2022Using Persuasive Writing Strategies to Explain and Detect Health Misinformationcited by 6
  15. 2023Unsupervised Improvement of Factual Knowledge in Language Modelscited by 6
  16. 2024Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responsescited by 6
  17. 2022Identifying and Characterizing Active Citizens who Refute Misinformation in Social Mediacited by 5
  18. 2023Unsupervised Pretraining for Fact Verification by Language Model Distillationcited by 5
  19. 2023Who Are All The Stochastic Parrots Imitating? They Should Tell Us!cited by 5
  20. 2024A Reality check of the benefits of LLM in businesscited by 5
  21. 2025Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learningcited by 5
  22. 2022Artefact Retrieval: Overview of NLP Models with Knowledge Base Accesscited by 4
  23. 2021WhatTheWikiFact: Fact-Checking Claims Against Wikipediacited by 3
  24. 2023Can large language models generate salient negative statements?cited by 3
  25. 2025Facts are Harder Than Opinions -- A Multilingual, Comparative Analysis of LLM-Based Fact-Checking Reliabilitycited by 3
  26. 2021Hostility Detection and Covid-19 Fake News Detection in Social Mediacited by 2
  27. 2025Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Searchcited by 2
  28. 2022Plot Writing From Pre-Trained Language Modelscited by 1
  29. 2023Understanding Breast Cancer Survival: Using Causality and Language Models on Multi-omics Datacited by 1
  30. 2023Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorialcited by 1
  31. 2024Generating Zero-shot Abstractive Explanations for Rumour Verificationcited by 1
  32. 2024Generative Debunking of Climate Misinformationcited by 1
  33. 2025GenAI vs. Human Fact-Checkers: Accurate Ratings, Flawed Rationalescited by 1
  34. 2025Entailed Opinion Matters: Improving the Fact-Checking Performance of Language Models by Relying on their Entailment Abilitycited by 1
  35. 2021Evidence-based Factual Error Correctioncited by 0
  36. 2026Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessitycited by 0
  37. 2026Can LLMs Take Retrieved Information with a Grain of Salt?cited by 0
  38. 2026Generating Biomedical Fact-Checking Reports with RL-Enhanced Agentic Searchcited by 0

50 most cited of 51 All 51 (JSON)