mlsanityData to 7 Oct 2026

ProoFVer: Natural Logic Theorem Proving for Fact Verification

arXiv 2108.11357 ↗First posted 25 Aug 2021cs.CLcited by 52

Not on the map. Why?

Abstract (arXiv)

Fact verification systems typically rely on neural network classifiers for veracity prediction which lack explainability. This paper proposes ProoFVer, which uses a seq2seq model to generate natural logic-based inferences as proofs. These proofs consist of lexical mutations between spans in the claim and the evidence retrieved, each marked with a natural logic operator. Claim veracity is determined solely based on the sequence of these operators. Hence, these proofs are faithful explanations, and this makes ProoFVer faithful by construction. Currently, ProoFVer has the highest label accuracy and the second-best Score in the FEVER leaderboard. Furthermore, it improves by 13.21% points over the next best model on a dataset with counterfactual instances, demonstrating its robustness. As explanations, the proofs show better overlap with human rationales than attention-based highlights and the proofs help humans predict model decisions correctly more often than using the evidence directly.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 42 of its 88 references that are in the map. First posted on arXiv 25 Aug 2021.

Builds on

42 of 88 references.

References · 42

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  2. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  3. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  4. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  5. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  6. 2016The Mythos of Model Interpretabilitycited by 716
  7. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  8. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  9. 2020Fact or Fiction: Verifying Scientific Claimscited by 546
  10. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  11. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  12. 2020Autoregressive Entity Retrievalcited by 333
30 more
  1. 2016Rationalizing Neural Predictionscited by 281
  2. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 222
  3. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 209
  4. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  5. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 166
  6. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 155
  7. 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
  8. 2020Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functionscited by 144
  9. 2019Towards Debiasing Fact Verification Modelscited by 143
  10. 2020Generating Fact Checking Explanationscited by 132
  11. 2020Learning to Faithfully Rationalize by Constructioncited by 113
  12. 2018The Fact Extraction and VERification (FEVER) Shared Taskcited by 108
  13. 2019Fine-grained Fact Verification with Kernel Graph Attention Networkcited by 105
  14. 2018DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learningcited by 100
  15. 2020Explainable Automated Fact-Checking: A Surveycited by 83
  16. 2020Coreferential Reasoning Learning for Language Representationcited by 80
  17. 2020Aligning Faithful Interpretations with their Social Attributioncited by 79
  18. 2019A Richly Annotated Corpus for Different Tasks in Automated Fact-Checkingcited by 74
  19. 2019Reasoning Over Semantic-Level Graph for Fact Checkingcited by 69
  20. 2018UKP-Athene: Multi-Sentence Textual Entailment for Claim Verificationcited by 60
  21. 2019Revealing the Importance of Semantic Retrieval for Machine Reading at Scalecited by 50
  22. 2020Generating Fact Checking Briefscited by 50
  23. 2020Evidence-based Factual Error Correctioncited by 44
  24. 2020EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraintscited by 24
  25. 2019Explainable Fact Checking with Probabilistic Answer Set Programmingcited by 23
  26. 2020DTCA: Decision Tree-based Co-Attention Networks for Explainable Claim Verificationcited by 17
  27. 2017LangPro: Natural Language Theorem Provercited by 15
  28. 2021multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoningcited by 15
  29. 2020Exploring End-to-End Differentiable Natural Logic Modelingcited by 9
  30. 2020Analyzing Wikidata Transclusion on English Wikipediacited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 12; 2024: 18; 2025: 8; 2026: 6.

52 papers.

Sort:

By area:

  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  2. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  3. 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
  4. 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
  5. 2023Scientific Fact-Checking: A Survey of Resources and Approachescited by 53
  6. 2022Generating Natural Language Proofs with Verifier-Guided Searchcited by 52
  7. 2023Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Modelscited by 31
  8. 2024JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claimscited by 29
  9. 2024Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMscited by 23
  10. 2024Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScorecited by 18
  11. 2023Atomic Inference for NLI with Generated Facts as Atomscited by 16
  12. 2024Automated Justification Production for Claim Veracity in Fact Checking: A Survey on Architectures and Approachescited by 15
38 more
  1. 2022Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Predictioncited by 12
  2. 2022Logical Satisfiability of Counterfactuals for Faithful Explanations in NLIcited by 11
  3. 2022Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verificationcited by 11
  4. 2023BEVERS: A General, Simple, and Performant Framework for Automatic Fact Verificationcited by 11
  5. 2022Converge to the Truth: Factual Error Correction via Iterative Constrained Editingcited by 9
  6. 2024CHECKWHY: Causal Fact Verification via Argument Structurecited by 9
  7. 2023QA-NatVer: Question Answering for Natural Logic-based Fact Verificationcited by 8
  8. 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemscited by 8
  9. 2024Towards a Framework for Evaluating Explanations in Automated Fact Verificationcited by 7
  10. 2024TANQ: An open domain dataset of table answered questionscited by 6
  11. 2023Unsupervised Pretraining for Fact Verification by Language Model Distillationcited by 5
  12. 2024The Critique of Critiquecited by 5
  13. 2024Zero-Shot Fact Verification via Natural Logic and Large Language Modelscited by 5
  14. 2025Verify-in-the-Graph: Entity Disambiguation Enhancement for Complex Claim Verification with Interactive Graph Representationcited by 5
  15. 2023Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Languagecited by 4
  16. 2024AMREx: AMR for Explainable Fact Verificationcited by 4
  17. 2024Robust Claim Verification Through Fact Detectioncited by 3
  18. 2024TabVer: Tabular Fact Verification with Natural Logiccited by 3
  19. 2023Evidence-based Interpretable Open-domain Fact-checking with Large Language Modelscited by 2
  20. 2024QuestGen: Effectiveness of Question Generation Methods for Fact-Checking Applicationscited by 2
  21. 2025MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphingcited by 2
  22. 2025Towards Unification of Hallucination Detection and Fact Verification for Large Language Modelscited by 2
  23. 2022Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problemcited by 1
  24. 2024Generating Zero-shot Abstractive Explanations for Rumour Verificationcited by 1
  25. 2024M3: A Multi-Task Mixed-Objective Learning Framework for Open-Domain Multi-Hop Dense Sentence Retrievalcited by 1
  26. 2024Multi-Evidence based Fact Verification via A Confidential Graph Neural Networkcited by 1
  27. 2025Reasoning Paths as Signals: Augmenting Multi-hop Fact Verification through Structural Reasoning Progressioncited by 1
  28. 2025The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detectioncited by 1
  29. 2026Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMscited by 1
  30. 2022Accountable and Explainable Methods for Complex Reasoning over Textcited by 0
  31. 2023Detrimental Contexts in Open-Domain Question Answeringcited by 0
  32. 2024Rethinking Loss Functions for Fact Verificationcited by 0
  33. 2024RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflictcited by 0
  34. 2025BERT-based model for Vietnamese Fact Verification Datasetcited by 0
  35. 2025On Finding Inconsistencies in Documentscited by 0
  36. 2026Mask-to-Correct^+: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correctioncited by 0
  37. 2026Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofscited by 0
  38. 2026Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledgecited by 0

50 most cited of 52 All 52 (JSON)