mlsanityData to 14 Oct 2026

The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers

arXiv 2506.20844 ↗First posted 25 Jun 2025cs.IR cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Scientific fact-checking aims to determine the veracity of scientific claims by retrieving and analysing evidence from research literature. The problem is inherently more complex than general fact-checking since it must accommodate the evolving nature of scientific knowledge, the structural complexity of academic literature and the challenges posed by long-form, multimodal scientific expression. However, existing approaches focus on simplified versions of the problem based on small-scale datasets consisting of abstracts rather than full papers, thereby avoiding the distinct challenges associated with processing complete documents. This paper examines the limitations of current scientific fact-checking systems and reveals the many potential features and resources that could be exploited to advance their performance. It identifies key research challenges within evidence retrieval, including (1) evidence-driven retrieval that addresses semantic limitations and topic imbalance (2) time-aware evidence retrieval with citation tracking to mitigate outdated information, (3) structured document parsing to leverage long-range context, (4) handling complex scientific expressions, including tables, figures, and domain-specific terminology and (5) assessing the credibility of scientific literature. Preliminary experiments were conducted to substantiate these challenges and identify potential solutions. This perspective paper aims to advance scientific fact-checking with a specialised IR system tailored for real-world applications.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 90 of its 120 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

90 of 120 references.

References · 90

  1. 2020Longformer: The Long-Document Transformercited by 3,413
  2. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,414
  3. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  4. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 1,009
  5. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  6. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  7. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  8. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 428
  9. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 398
  10. 2021A Survey on Automated Fact-Checkingcited by 378
  11. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  12. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
38 more
  1. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
  2. 2020Overview of the TREC 2019 deep learning trackcited by 286
  3. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
  4. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 211
  5. 2020CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claimscited by 196
  6. 2021Overview of the TREC 2020 deep learning trackcited by 196
  7. 2024MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizationscited by 183
  8. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 179
  9. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 178
  10. 2019MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claimscited by 169
  11. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 151
  12. 2023AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Webcited by 144
  13. 2021MultiVerS: Improving scientific claim verification with weak supervision and full-document contextcited by 143
  14. 2024M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understandingcited by 111
  15. 2018The Fact Extraction and VERification (FEVER) Shared Taskcited by 108
  16. 2022End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Modelscited by 107
  17. 2021COVID-Fact: Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemiccited by 100
  18. 2022SciFact-Open: Towards open-domain scientific claim verificationcited by 94
  19. 2024Evaluating Retrieval Quality in Retrieval-Augmented Generationcited by 90
  20. 2023Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkerscited by 87
  21. 2024One Thousand and One Pairs: A "novel" challenge for long-context language modelscited by 80
  22. 2024SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detectioncited by 74
  23. 2021Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resourcescited by 71
  24. 2023FactKG: Fact Verification via Reasoning on Knowledge Graphscited by 57
  25. 2021Automated Fact-Checking: A Surveycited by 55
  26. 2023Scientific Fact-Checking: A Survey of Resources and Approachescited by 54
  27. 2023Multimodal Automated Fact-Checking: A Surveycited by 53
  28. 2023SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tablescited by 51
  29. 2024SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretationcited by 48
  30. 2018BioSentVec: creating sentence embeddings for biomedical textscited by 47
  31. 2020Scientific Claim Verification with VERT5ERINIcited by 47
  32. 2022PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-trainingcited by 41
  33. 2023VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Biascited by 39
  34. 2020Citation Recommendation: Approaches and Datasetscited by 36
  35. 2023Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checkingcited by 35
  36. 2020A Paragraph-level Multi-task Learning Model for Scientific Fact-Verificationcited by 29
  37. 2022CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweetscited by 29
  38. 2024Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximizationcited by 29

50 most cited of 90 All 90 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025+VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checkingcited by 2
  2. 2026From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidencecited by 1
  3. 2026Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learningcited by 0
  4. 2026ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claimscited by 0
  5. 2026Does Finetuning with Scientific Data Increase Hallucinations? A Multi-domain Factuality Evaluation of LLMscited by 0
  6. 2026Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablationcited by 0