mlsanityData to 7 Oct 2026

Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning

arXiv 2502.14765 ↗First posted 20 Feb 2025cs.CL cs.AIcited by 17

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Fact verification (FV) aims to assess the veracity of a claim based on relevant evidence. The traditional approach for automated FV includes a three-part pipeline relying on short evidence snippets and encoder-only inference models. More recent approaches leverage the multi-turn nature of LLMs to address FV as a step-by-step problem where questions inquiring additional context are generated and answered until there is enough information to make a decision. This iterative method makes the verification process rational and explainable. While these methods have been tested for encyclopedic claims, exploration on domain-specific and realistic claims is missing. In this work, we apply an iterative FV system on three medical fact-checking datasets and evaluate it with multiple settings, including different LLMs, external web search, and structured reasoning using logic predicates. We demonstrate improvements in the final performance over traditional approaches and the high potential of step-by-step FV systems for domain-specific claims.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 7 of its 48 references that are in the map. First posted on arXiv 20 Feb 2025.

Builds on

7 of 48 references.

References · 7

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2024Mixtral of Expertscited by 1,785
  4. 2020CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claimscited by 195
  5. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 41
  6. 2025Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checkingcited by 29
  7. 2024Claim Verification in the Age of Large Language Models: A Surveycited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 9.

17 papers.

Sort:

By area:

  1. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Modelscited by 13
  2. 2025ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentationcited by 12
  3. 2025Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learningcited by 5
  4. 2025Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledgecited by 3
  5. 2025SciClaims: An End-to-End Generative System for Biomedical Claim Analysiscited by 2
  6. 2026Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attributioncited by 2
  7. 2026Neurosymbolic Learning for Inference-Time Argumentationcited by 2
  8. 2025VERIRAG: A Post-Retrieval Auditing of Scientific Study Summariescited by 1
  9. 2026Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMscited by 1
  10. 2026Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verificationcited by 1
  11. 2025Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Studycited by 0
  12. 2025Exploring Health Misinformation Detection with Multi-Agent Debatecited by 0
5 more
  1. 2026ART: Adaptive Reasoning Trees for Explainable Claim Verificationcited by 0
  2. 2026MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessmentcited by 0
  3. 2026When Verification Fails: How Compositionally Infeasible Claims Escape Rejectioncited by 0
  4. 2026What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QAcited by 0
  5. 2026An Agentic RAG and Evaluation Framework for Assurance Case Generation: Industrial Use Case for the EU Cyber Resilience Act Compliancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Evidence-based Interpretable Open-domain Fact-checking with Large Language Models
  2. 2025Combating Biomedical Misinformation through Multi-modal Claim Detection and Evidence-based Verification
  3. 2025Explainable Biomedical Claim Verification with Large Language Models
  4. 2023Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models
  5. 2025Combining Evidence and Reasoning for Biomedical Fact-Checking
  6. 2025Towards Automated Fact-Checking of Real-World Claims: Exploring Task Formulation and Assessment with LLMs
  7. 2025Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification
  8. 2026Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation