# A Specialized Large Language Model for Clinical Reasoning and Diagnosis in Rare Diseases

arXiv: https://arxiv.org/abs/2511.14638 · HTML: https://mlsanity.com/paper/2511.14638/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- First posted on arXiv 18 Nov 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Built on by (most cited first, 3 of 3)

- [Teaching agentic AI to generalize expert diagnostic reasoning in rare diseases](https://mlsanity.com/paper/2606.16149/) (2026)
- [An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models](https://mlsanity.com/paper/2602.20324/) (2026)
- [One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail](https://mlsanity.com/paper/2608.14683/) (2026)

## Abstract (arXiv)

Rare diseases affect hundreds of millions worldwide, yet diagnosis often spans years. Convectional pipelines decouple noisy evidence extraction from downstream inferential diagnosis, and general/medical large language models (LLMs) face scarce real world electronic health records (EHRs), stale domain knowledge, and hallucinations. We assemble a large, domain specialized clinical corpus and a clinician validated reasoning set, and develop RareSeek R1 via staged instruction tuning, chain of thought learning, and graph grounded retrieval. Across multicenter EHR narratives and public benchmarks, RareSeek R1 attains state of the art accuracy, robust generalization, and stability under noisy or overlapping phenotypes. Augmented retrieval yields the largest gains when narratives pair with prioritized variants by resolving ambiguity and aligning candidates to mechanisms. Human studies show performance on par with experienced physicians and consistent gains in assistive use. Notably, transparent reasoning highlights decisive non phenotypic evidence (median 23.1%, such as imaging, interventions, functional tests) underpinning many correct diagnoses. This work advances a narrative first, knowledge integrated reasoning paradigm that shortens the diagnostic odyssey and enables auditable, clinically translatable decision support.