mlsanityData to 14 Oct 2026

Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verification

arXiv 2110.15116 ↗First posted 13 Sep 2021cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Scientific claim verification can help the researchers to easily find the target scientific papers with the sentence evidence from a large corpus for the given claim. Some existing works propose pipeline models on the three tasks of abstract retrieval, rationale selection and stance prediction. Such works have the problems of error propagation among the modules in the pipeline and lack of sharing valuable information among modules. We thus propose an approach, named as ARSJoint, that jointly learns the modules for the three tasks with a machine reading comprehension framework by including claim information. In addition, we enhance the information exchanges and constraints among tasks by proposing a regularization term between the sentence attention scores of abstract retrieval and the estimated outputs of rational selection. The experimental results on the benchmark dataset SciFact show that our approach outperforms the existing works.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 21 of its 26 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

21 of 26 references.

References · 21

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  4. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  5. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  6. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
  7. 2019Attention is not not Explanationcited by 636
  8. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  9. 2019Is Attention Interpretable?cited by 389
  10. 2018Combining Fact Extraction and Verification with Neural Semantic Matching Networkscited by 120
  11. 2020GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Mediacited by 109
  12. 2019Fine-grained Fact Verification with Kernel Graph Attention Networkcited by 105
9 more
  1. 2017Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Featurescited by 104
  2. 2019GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verificationcited by 100
  3. 2019BERT for Evidence Retrieval and Claim Verificationcited by 57
  4. 2018BioSentVec: creating sentence embeddings for biomedical textscited by 47
  5. 2020Scientific Claim Verification with VERT5ERINIcited by 47
  6. 2020A Paragraph-level Multi-task Learning Model for Scientific Fact-Verificationcited by 29
  7. 2020DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checkingcited by 26
  8. 2018TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verificationcited by 17
  9. 2020Misinformation Has High Perplexitycited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 2; 2024: 4; 2025: 4; 2026: 3.

20 papers.

Sort:

  1. 2021MultiVerS: Improving scientific claim verification with weak supervision and full-document contextcited by 143
  2. 2022SciFact-Open: Towards open-domain scientific claim verificationcited by 94
  3. 2023Scientific Fact-Checking: A Survey of Resources and Approachescited by 54
  4. 2023BEVERS: A General, Simple, and Performant Framework for Automatic Fact Verificationcited by 11
  5. 2024Comparing Knowledge Sources for Open-Domain Scientific Claim Verificationcited by 10
  6. 2025Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Sciencecited by 9
  7. 2022Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweetscited by 7
  8. 2022Combating Health Misinformation in Social Media: Characterization, Detection, Intervention, and Open Issuescited by 6
  9. 2025The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Paperscited by 6
  10. 2022RerrFact: Reduced Evidence Retrieval Representations for Scientific Claim Verificationcited by 5
  11. 2022Active PETs: Active Data Annotation Prioritisation for Few-Shot Claim Verification with Pattern Exploiting Trainingcited by 5
  12. 2024MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verificationcited by 5
8 more
  1. 2024Minimal Evidence Group Identification for Claim Verificationcited by 5
  2. 2025CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checkingcited by 5
  3. 2024Robust Claim Verification Through Fact Detectioncited by 3
  4. 2025+VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checkingcited by 2
  5. 2026Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attributioncited by 2
  6. 2022ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Paperscited by 1
  7. 2026MEVER: Multi-Modal and Explainable Claim Verification with Graph-based Evidence Retrievalcited by 0
  8. 2026Detection and Interpretability Analysis of Quotation Errors by Large Language Modelscited by 0