mlsanityData to 14 Oct 2026

Zero-shot Fact Verification by Claim Generation

arXiv 2105.14682 ↗First posted 31 May 2021cs.CL cs.AIcited by 42

Not on the map. Why?

Abstract (arXiv)

Neural models for automated fact verification have achieved promising results thanks to the availability of large, human-annotated datasets. However, for each new domain that requires fact verification, creating a dataset by manually writing claims and linking them to their supporting evidence is expensive. We develop QACG, a framework for training a robust fact verification model by using automatically generated claims that can be supported, refuted, or unverifiable from evidence from Wikipedia. QACG generates question-answer pairs from the evidence and then converts them into different types of claims. Experiments on the FEVER dataset show that our QACG framework significantly reduces the demand for human-annotated training data. In a zero-shot scenario, QACG improves a RoBERTa model's F1 from 50% to 77%, equivalent in performance to 2K+ manually-curated examples. Our QACG code is publicly available.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

22 of 33 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  5. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  6. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  7. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 670
  8. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 378
  9. 2019Synthetic QA Corpora Generation with Roundtrip Consistencycited by 143
  10. 2019Towards Debiasing Fact Verification Modelscited by 143
  11. 2019Fine-grained Fact Verification with Kernel Graph Attention Networkcited by 105
  12. 2019GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verificationcited by 100
10 more
  1. 2018Transforming Question Answering Datasets Into Natural Language Inference Datasetscited by 99
  2. 2017Neural Question Generation from Text: A Preliminary Studycited by 78
  3. 2019Reasoning Over Semantic-Level Graph for Fact Checkingcited by 69
  4. 2020Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpuscited by 40
  5. 2020Semantic Graphs for Generating Deep Questionscited by 38
  6. 2020Generating Label Cohesive and Well-Formed Adversarial Claimscited by 27
  7. 2018Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generationcited by 25
  8. 2015sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddingscited by 20
  9. 2020Misinformation Has High Perplexitycited by 15
  10. 2019Team Papelo: Transformer Networks at FEVERcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 6; 2023: 13; 2024: 9; 2025: 6; 2026: 2.

42 papers.

Sort:

By area:

  1. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  2. 2021A Survey on Automated Fact-Checkingcited by 378
  3. 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
  4. 2022Generating Scientific Claims for Zero-Shot Scientific Fact Checkingcited by 59
  5. 2021Attacking Open-domain Question Answering by Injecting Misinformationcited by 41
  6. 2023Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Modelscited by 37
  7. 2021FaVIQ: FAct Verification from Information-seeking Questionscited by 36
  8. 2021MixQG: Neural Question Generation with Mixed Answer Typescited by 28
  9. 2023Zero-shot Faithful Factual Error Correctioncited by 26
  10. 2024Claim Verification in the Age of Large Language Models: A Surveycited by 24
  11. 2024Reinforcement Retrieval Leveraging Fine-grained Feedback for Fact Checking News Claims with Black-Box LLMcited by 15
  12. 2024MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedbackcited by 14
30 more
  1. 2023FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generationcited by 12
  2. 2021BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddlescited by 10
  3. 2023SWING: Balancing Coverage and Faithfulness for Dialogue Summarizationcited by 10
  4. 2022Ask to Know More: Generating Counterfactual Explanations for Fake Claimscited by 8
  5. 2023SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examplescited by 8
  6. 2023QA-NatVer: Question Answering for Natural Logic-based Fact Verificationcited by 8
  7. 2023Zero-Shot Fact-Checking with Semantic Triples and Knowledge Graphscited by 8
  8. 2022Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweetscited by 7
  9. 2023Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Modelscited by 6
  10. 2022Active PETs: Active Data Annotation Prioritisation for Few-Shot Claim Verification with Pattern Exploiting Trainingcited by 5
  11. 2022Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AIcited by 5
  12. 2024A Survey on Neural Question Generation: Methods, Applications, and Prospectscited by 5
  13. 2024Zero-Shot Fact Verification via Natural Logic and Large Language Modelscited by 5
  14. 2025Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learningcited by 5
  15. 2023Investigating Zero- and Few-shot Generalization in Fact Verificationcited by 4
  16. 2023Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Languagecited by 4
  17. 2025MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMscited by 4
  18. 2023SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoningcited by 3
  19. 2024Robust Claim Verification Through Fact Detectioncited by 3
  20. 2022Consecutive Question Generation via Dynamic Multitask Learningcited by 2
  21. 2023Ask To The Point: Open-Domain Entity-Centric Question Generationcited by 2
  22. 2025Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questionscited by 2
  23. 2025SciClaims: An End-to-End Generative System for Biomedical Claim Analysiscited by 2
  24. 2024Multi-Evidence based Fact Verification via A Confidential Graph Neural Networkcited by 1
  25. 2024MODOC: A Modular Interface for Flexible Interlinking of Text Retrieval and Text Generation Functionscited by 1
  26. 2024FinGen: A Dataset for Argument Generation in Financecited by 0
  27. 2025Application and Optimization of Large Models Based on Prompt Tuning for Fact-Check-Worthiness Estimationcited by 0
  28. 2025EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detectioncited by 0
  29. 2026ARAFA: An LLM-Generated Arabic Fact-Checking Datasetcited by 0
  30. 2026RelCheck: Dual-Evidence Spatial Grounding for VLM Hallucination Correctioncited by 0