# VeriDx: Earning the Right to Diagnose with Disease-Centric Verification

arXiv: https://arxiv.org/abs/2609.14018 · HTML: https://mlsanity.com/paper/2609.14018/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 29 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 5 of 5)

- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval](https://mlsanity.com/paper/2410.04585/) (2024)
- [MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks](https://mlsanity.com/paper/2505.12371/) (2025)
- [Multi-Agent Reasoning with Consistency Verification Improves Uncertainty Calibration in Medical MCQA](https://mlsanity.com/paper/2603.24481/) (2026)

## Abstract (arXiv)

A correct diagnosis can still be reached for the wrong reasons. In clinical reasoning, every disease hypothesis creates obligations: key evidence must be checked, alternatives must be ruled out, contradictions must be resolved, useful tests must be considered, and closure must be justified. Current evaluations of medical LLMs mostly focus on final answers, local steps, or isolated facts, and therefore miss these hypothesis-induced commitments. We introduce VeriDx, a disease-centric verification framework that links free-form diagnostic reasoning to structured disease profiles. VeriDx tracks whether each hypothesis is satisfied, unresolved, or violated its clinical obligations, exposing failures such as missing critical tests, unresolved differentials, ignored contradictions, unsupported claims, and premature closure. We instantiate VeriDx for complex respiratory diagnosis using guideline-derived disease profiles and expert-annotated longitudinal cases. Our results show that many diagnostic errors are not isolated mistakes, but broken commitments made earlier in the reasoning process.