Automated Fact Checking: Task formulations, methods and future directions
Not on the map. Why?
Abstract (arXiv)
The recently increased focus on misinformation has stimulated research in fact checking, the task of assessing the truthfulness of a claim. Research in automating this task has been conducted in a variety of disciplines including natural language processing, machine learning, knowledge representation, databases, and journalism. While there has been substantial progress, relevant papers and articles have been published in research communities that are often unaware of each other and use inconsistent terminology, thus impeding understanding and further progress. In this paper we survey automated fact checking research stemming from natural language processing and related disciplines, unifying the task formulations and methodologies across papers and authors. Furthermore, we highlight the use of evidence as an important distinguishing factor among them cutting across task formulations and methods. We conclude with proposing avenues for future NLP research on automated fact checking.
Key facts. Cited by 96 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Jun 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 32; 2022: 17; 2023: 10; 2024: 15; 2025: 10; 2026: 12.
96 papers.
Sort:
By area:
- 2021A Survey on Automated Fact-Checkingcited by 378
- 2021Measuring Attribution in Natural Language Generation Modelscited by 256
- 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 230
- 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 225
- 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 167
- 2024Fine-grained Hallucination Detection and Editing for Language Modelscited by 149
- 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
- 2021Automated Fact-Checking for Assisting Human Fact-Checkerscited by 144
- 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 138
- 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 132
- 2021A Survey on Stance Detection for Mis- and Disinformation Identificationcited by 75
- 2021Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resourcescited by 71
38 more
- 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
- 2021Automated Fact-Checking: A Surveycited by 55
- 2023Scientific Fact-Checking: A Survey of Resources and Approachescited by 54
- 2023Multimodal Automated Fact-Checking: A Surveycited by 53
- 2023Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrongcited by 51
- 2021A Survey on Multimodal Disinformation Detectioncited by 47
- 2022Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformationcited by 45
- 2022Synthetic Disinformation Attacks on Automated Fact Verification Systemscited by 44
- 2021AmbiFC: Fact-Checking Ambiguous Claims with Evidencecited by 38
- 2022CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweetscited by 29
- 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievalscited by 28
- 2024Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMscited by 24
- 2024QuanTemp: A real-world open-domain benchmark for fact-checking numerical claimscited by 23
- 2023An Overview on Language Models: Recent Developments and Outlookcited by 22
- 2021A Survey on Predicting the Factuality and the Bias of News Mediacited by 20
- 2021Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Documentcited by 19
- 2023The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Whocited by 19
- 2024Generative Large Language Models in Automated Fact-Checking: A Surveycited by 19
- 2021The Role of Context in Detecting Previously Fact-Checked Claimscited by 17
- 2022Crowdsourced Fact-Checking at Twitter: How Does the Crowd Compare With Experts?cited by 16
- 2022Matching Tweets With Applicable Fact-Checks Across Languagescited by 15
- 2024Automated Justification Production for Claim Veracity in Fact Checking: A Survey on Architectures and Approachescited by 15
- 2021Transformer based Automatic COVID-19 Fake News Detection Systemcited by 14
- 2021Findings of the NLP4IF-2021 Shared Tasks on Fighting the COVID-19 Infodemic and Censorship Detectioncited by 14
- 2021Misinformation Detection on YouTube Using Video Captionscited by 12
- 2022Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systemscited by 12
- 2024Piecing It All Together: Verifying Multi-Hop Multimodal Claimscited by 12
- 2021Dataset of Fake News Detection and Fact Verification: A Surveycited by 11
- 2022Improving Wikipedia Verifiability with AIcited by 11
- 2021FacTeR-Check: Semi-automated fact-checking through Semantic Similarity and Natural Language Inferencecited by 10
- 2022Evaluation of Fake News Detection with Knowledge-Enhanced Language Modelscited by 9
- 2021Extractive and Abstractive Explanations for Fact-Checking and Evaluation of Newscited by 8
- 2023Identifying Conspiracy Theories News based on Event Relation Graphcited by 8
- 2023Are Large Language Models Good Fact Checkers: A Preliminary Studycited by 8
- 2025BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checkingcited by 8
- 2021Automatic Fake News Detection: Are Models Learning to Reason?cited by 7
- 2022Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweetscited by 7
- 2023Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoningcited by 7
50 most cited of 96 All 96 (JSON)
- 2026ARAFA: An LLM-Generated Arabic Fact-Checking Dataset22 Sep 2026
- 2026How Robust Are Automated Fact-Checking Systems? A Cross-Benchmark Evaluation26 Aug 2026
- 2026A Cognitively Grounded Bayesian Framework for Misinformation Susceptibility10 May 2026
- 2026An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation23 Apr 2026
- 2026Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models23 Apr 2026
- 2026BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking15 Apr 2026
- 2026Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM21 Feb 2026
- 2026Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectiveness15 Feb 2026
- 2026DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems31 Jan 2026
- 2026Retrieve-Refine-Calibrate: A Framework for Complex Claim Fact-Checking23 Jan 2026
- 2026Global Consistency Repair for Natural-Language Claim Sets20 Jan 2026
- 2026Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency5 Jan 2026
38 more
- 2025Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation18 Dec 2025
- 2025Categorical Emotions or Appraisals - Which Emotion Model Explains Argument Convincingness Better?10 Nov 2025
- 2025ShortCheck: Checkworthiness Detection of Multilingual Short-Form Videos24 Sep 2025
- 2025ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLM28 May 2025
- 2025Assessing the Potential of Generative Agents in Crowdsourced Fact-Checking24 Apr 2025
- 2025FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text19 Mar 2025
- 2025Fact-checking with Generative AI: A Systematic Cross-Topic Examination of LLMs Capacity to Detect Veracity of Political Information11 Mar 2025
- 2025BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking22 Feb 2025
- 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals22 Feb 2025
- 2025Fine-Grained Appropriate Reliance: Human-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decomposition19 Jan 2025
- 2024Piecing It All Together: Verifying Multi-Hop Multimodal Claims14 Nov 2024
- 2024A Comparative Study of Translation Bias and Accuracy in Multilingual Large Language Models for Cross-Language Claim Verification14 Oct 2024
- 2024How Entangled is Factuality and Deception in German?30 Sep 2024
- 2024Enhancing Natural Language Inference Performance with Knowledge Graph for COVID-19 Automated Fact-Checking in Indonesian Language22 Aug 2024
- 2024Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs22 Aug 2024
- 2024Fact or Fiction? Improving Fact Verification with Knowledge Graphs through Simplified Subgraph Retrievals14 Aug 2024
- 2024Automated Justification Production for Claim Veracity in Fact Checking: A Survey on Architectures and Approaches9 Jul 2024
- 2024HYBRINFOX at CheckThat! 2024 -- Task 1: Enhancing Language Models with Structured Information for Check-Worthiness Estimation4 Jul 2024
- 2024Generative Large Language Models in Automated Fact-Checking: A Survey2 Jul 2024
- 2024Fact Checking Beyond Training Set27 Mar 2024
- 2024QuanTemp: A real-world open-domain benchmark for fact-checking numerical claims25 Mar 2024
- 2024Can Factual Statements be Deceptive? The DeFaBel Corpus of Belief-based Deception15 Mar 2024
- 2024Textual Entailment for Effective Triple Validation in Object Prediction29 Jan 2024
- 2024MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification29 Jan 2024
- 2024Fine-grained Hallucination Detection and Editing for Language Models12 Jan 2024
- 2023Are Large Language Models Good Fact Checkers: A Preliminary Study29 Nov 2023
- 2023Identifying Conspiracy Theories News based on Event Relation Graph28 Oct 2023
- 2023Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong19 Oct 2023
- 2023Entailment as Robust Self-Learner26 May 2023
- 2023Scientific Fact-Checking: A Survey of Resources and Approaches26 May 2023
- 2023Multimodal Automated Fact-Checking: A Survey22 May 2023
- 2023Fact-Checking Complex Claims with Program-Guided Reasoning22 May 2023
- 2023The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who27 Apr 2023
- 2023An Overview on Language Models: Recent Developments and Outlook10 Mar 2023
- 2023Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning10 Mar 2023
- 2022ProVe: A Pipeline for Automated Provenance Verification of Knowledge Graphs against Textual Sources26 Oct 2022
- 2022Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation25 Oct 2022
- 2022Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweets16 Sep 2022
50 newest of 96 All 96 (JSON)
- 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
- 2023Are Large Language Models Good Fact Checkers: A Preliminary Studycited by 8
- 2025ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLMcited by 2
- 2026Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectivenesscited by 1
- 2026Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectiveness15 Feb 2026
- 2025ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLM28 May 2025
- 2023Are Large Language Models Good Fact Checkers: A Preliminary Study29 Nov 2023
- 2023Fact-Checking Complex Claims with Program-Guided Reasoning22 May 2023
- 2021A Survey on Automated Fact-Checkingcited by 378
- 2021Measuring Attribution in Natural Language Generation Modelscited by 256
- 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 230
- 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 225
- 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 167
- 2024Fine-grained Hallucination Detection and Editing for Language Modelscited by 149
- 2021Automated Fact-Checking for Assisting Human Fact-Checkerscited by 144
- 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 138
- 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 132
- 2021A Survey on Stance Detection for Mis- and Disinformation Identificationcited by 75
- 2021Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resourcescited by 71
- 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
12 most cited of 88 All 88 (JSON)
- 2026ARAFA: An LLM-Generated Arabic Fact-Checking Dataset22 Sep 2026
- 2026How Robust Are Automated Fact-Checking Systems? A Cross-Benchmark Evaluation26 Aug 2026
- 2026A Cognitively Grounded Bayesian Framework for Misinformation Susceptibility10 May 2026
- 2026Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models23 Apr 2026
- 2026BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking15 Apr 2026
- 2026Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM21 Feb 2026
- 2026DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems31 Jan 2026
- 2026Retrieve-Refine-Calibrate: A Framework for Complex Claim Fact-Checking23 Jan 2026
- 2026Global Consistency Repair for Natural-Language Claim Sets20 Jan 2026
- 2026Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency5 Jan 2026
- 2025Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation18 Dec 2025
- 2025Categorical Emotions or Appraisals - Which Emotion Model Explains Argument Convincingness Better?10 Nov 2025
12 newest of 88 All 88 (JSON)