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

arXiv: https://arxiv.org/abs/2502.14765 · HTML: https://mlsanity.com/paper/2502.14765/

## Key facts

- Cited by 17 papers in the map (data through 14 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.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 7 of 7)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation](https://mlsanity.com/paper/2502.05151/) (2025)
- [Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking](https://mlsanity.com/paper/2502.09083/) (2025)
- [Claim Verification in the Age of Large Language Models: A Survey](https://mlsanity.com/paper/2408.14317/) (2024)

## Built on by (most cited first, 17 of 17)

- [Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models](https://mlsanity.com/paper/2508.03860/) (2025)
- [ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation](https://mlsanity.com/paper/2508.20131/) (2025)
- [Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning](https://mlsanity.com/paper/2510.01932/) (2025)
- [Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledge](https://mlsanity.com/paper/2506.19607/) (2025)
- [SciClaims: An End-to-End Generative System for Biomedical Claim Analysis](https://mlsanity.com/paper/2503.18526/) (2025)
- [Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution](https://mlsanity.com/paper/2603.05308/) (2026)
- [Neurosymbolic Learning for Inference-Time Argumentation](https://mlsanity.com/paper/2605.20098/) (2026)
- [VERIRAG: A Post-Retrieval Auditing of Scientific Study Summaries](https://mlsanity.com/paper/2507.17948/) (2025)
- [Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs](https://mlsanity.com/paper/2604.04177/) (2026)
- [Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verification](https://mlsanity.com/paper/2605.26663/) (2026)
- [Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study](https://mlsanity.com/paper/2508.09776/) (2025)
- [Exploring Health Misinformation Detection with Multi-Agent Debate](https://mlsanity.com/paper/2512.09935/) (2025)
- [ART: Adaptive Reasoning Trees for Explainable Claim Verification](https://mlsanity.com/paper/2601.05455/) (2026)
- [MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment](https://mlsanity.com/paper/2601.22361/) (2026)
- [When Verification Fails: How Compositionally Infeasible Claims Escape Rejection](https://mlsanity.com/paper/2604.10990/) (2026)
- [What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA](https://mlsanity.com/paper/2605.25988/) (2026)
- [An Agentic RAG and Evaluation Framework for Assurance Case Generation: Industrial Use Case for the EU Cyber Resilience Act Compliance](https://mlsanity.com/paper/2608.19509/) (2026)

## 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.