mlsanityData to 7 Oct 2026

MultiVerS: Improving scientific claim verification with weak supervision and full-document context

arXiv 2112.01640 ↗First posted 2 Dec 2021cs.CL cs.AIcited by 140

Not on the map. Why?

Abstract (arXiv)

The scientific claim verification task requires an NLP system to label scientific documents which Support or Refute an input claim, and to select evidentiary sentences (or rationales) justifying each predicted label. In this work, we present MultiVerS, which predicts a fact-checking label and identifies rationales in a multitask fashion based on a shared encoding of the claim and full document context. This approach accomplishes two key modeling goals. First, it ensures that all relevant contextual information is incorporated into each labeling decision. Second, it enables the model to learn from instances annotated with a document-level fact-checking label, but lacking sentence-level rationales. This allows MultiVerS to perform weakly-supervised domain adaptation by training on scientific documents labeled using high-precision heuristics. Our approach outperforms two competitive baselines on three scientific claim verification datasets, with particularly strong performance in zero / few-shot domain adaptation experiments. Our code and data are available at https://github.com/dwadden/multivers.

Key facts. Cited by 140 papers in the map (data through 7 Oct 2026). Builds on 30 of its 40 references that are in the map. First posted on arXiv 2 Dec 2021.

Builds on

30 of 40 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,935
  6. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  8. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  9. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  10. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  11. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  12. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 996
18 more
  1. 2020Fact or Fiction: Verifying Scientific Claimscited by 546
  2. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  3. 2016Rationalizing Neural Predictionscited by 281
  4. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 209
  5. 2020CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claimscited by 195
  6. 2020CORD-19: The COVID-19 Open Research Datasetcited by 179
  7. 2021Decontextualization: Making Sentences Stand-Alonecited by 101
  8. 2021COVID-Fact: Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemiccited by 100
  9. 2020An Information Bottleneck Approach for Controlling Conciseness in Rationale Extractioncited by 69
  10. 2019Inferring Which Medical Treatments Work from Reports of Clinical Trialscited by 63
  11. 2021Towards Few-Shot Fact-Checking via Perplexitycited by 63
  12. 2020Scientific Claim Verification with VERT5ERINIcited by 47
  13. 2020Evidence Inference 2.0: More Data, Better Modelscited by 39
  14. 2020A Paragraph-level Multi-task Learning Model for Scientific Fact-Verificationcited by 29
  15. 2021Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verificationcited by 20
  16. 2021Overview and Insights from the SciVer Shared Task on Scientific Claim Verificationcited by 17
  17. 2020Weakly- and Semi-supervised Evidence Extractioncited by 16
  18. 2020Understanding Clinical Trial Reports: Extracting Medical Entities and Their Relationscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 11; 2023: 31; 2024: 43; 2025: 31; 2026: 24.

140 papers.

Sort:

By area:

  1. 2022The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluationcited by 133
  2. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 86
  3. 2023Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Promptingcited by 80
  4. 2023SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Modelscited by 72
  5. 2024Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translationcited by 62
  6. 2022Handling Bias in Toxic Speech Detection: A Surveycited by 60
  7. 2023The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Valuescited by 53
  8. 2023Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Informationcited by 52
  9. 2022Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Modelscited by 51
  10. 2023SemEval-2023 Task 10: Explainable Detection of Online Sexismcited by 48
  11. 2023The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographicscited by 45
  12. 2024VariErr NLI: Separating Annotation Error from Human Label Variationcited by 42
38 more
  1. 2024Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challengescited by 42
  2. 2024The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labelscited by 37
  3. 2022Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Expertscited by 36
  4. 2024LMUnit: Fine-grained Evaluation with Natural Language Unit Testscited by 32
  5. 2025Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptionscited by 31
  6. 2024The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representationcited by 29
  7. 2024Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directionscited by 26
  8. 2023NBIAS: A Natural Language Processing Framework for Bias Identification in Textcited by 23
  9. 2024Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personascited by 23
  10. 2024Hate Personified: Investigating the role of LLMs in content moderationcited by 23
  11. 2023Consistency is Key: Disentangling Label Variation in Natural Language Processing with Intra-Annotator Agreementcited by 22
  12. 2023What's the Meaning of Superhuman Performance in Today's NLU?cited by 22
  13. 2023Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Languagecited by 22
  14. 2023How Far Can We Extract Diverse Perspectives from Large Language Models?cited by 22
  15. 2025IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistancecited by 22
  16. 2024Conformalized Credal Set Predictorscited by 21
  17. 2024Personas with Attitudes: Controlling LLMs for Diverse Data Annotationcited by 21
  18. 2024The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youthcited by 20
  19. 2023What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronounscited by 19
  20. 2022Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitionscited by 18
  21. 2023Don't Waste a Single Annotation: Improving Single-Label Classifiers Through Soft Labelscited by 17
  22. 2023''Fifty Shades of Bias'': Normative Ratings of Gender Bias in GPT Generated English Textcited by 15
  23. 2024Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?cited by 15
  24. 2024LLM Roleplay: Simulating Human-Chatbot Interactioncited by 15
  25. 2023Modeling Empathic Similarity in Personal Narrativescited by 14
  26. 2024Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Datasetcited by 13
  27. 2022AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detectioncited by 12
  28. 2024A Prompt Response to the Demand for Automatic Gender-Neutral Translationcited by 12
  29. 2024HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twittercited by 12
  30. 2022Explainable Abuse Detection as Intent Classification and Slot Fillingcited by 11
  31. 2023"One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviorscited by 11
  32. 2024Risks and Opportunities of Open-Source Generative AIcited by 11
  33. 2024PEFT-U: Parameter-Efficient Fine-Tuning for User Personalizationcited by 11
  34. 2024Subjective textitIsms? On the Danger of Conflating Hate and Offence in Abusive Language Detectioncited by 9
  35. 2024NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Datacited by 9
  36. 2024D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluationcited by 9
  37. 2024Voices in a Crowd: Searching for Clusters of Unique Perspectivescited by 9
  38. 2024Discipline and Label: A WEIRD Genealogy and Social Theory of Data Annotationcited by 8

50 most cited of 140 All 140 (JSON)