arXiv Computation and Language September 3, 2026 By Zhaoyang Jiang, Zhizhong Fu, Yunsoo Kim, Zicheng Li, Xuanqi Peng, Fei Teng, Jiacong Mi, Honghan Wu

Learning to Fuse LLMs with Ontology Rankers for Rare-Disease Diagnosis

Read the original on arXiv Computation and Language →

The paper proposes a behavior-based fusion model that combines large language models (LLMs) with ontology rankers to improve rare-disease diagnosis. By examining ranked lists, agreement, and ontology support, the model learns how much to rely on each system per case, achieving significant recall gains on Phenopacket Store and RAMEDIS benchmarks. Importantly, the fused diagnoses retain candidate-level ontology evidence for inspection.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Sep 10

OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints?

arXiv:2609.08174v1 Announce Type: new Abstract: We introduce OntologyBench, a tiered biomedical retrieval benchmark comprising 471,854 training and 125,744 evaluation query-document relevance pairs a...

By Xiao Yu Cindy Zhang, Wyeth Wasserman, Jian Zhu

llms rag fine-tuning benchmarks

arXiv AI

Jun 16

LiteOdyssey: A Lightweight Reasoning AI Agent for Interpretable Rare-Disease Diagnosis

arXiv:2606. 16149v1 Announce Type: new Abstract: Most medical AI systems improve by scaling additional machinery: more fine-tuning data, more agents, and/or larger retrieval databases.

By Minh-Ha Nguyen, Erica Gray, Chih-Ting Yang, Rizwan Hamid, Lingyao Li, Siyuan Ma, Thomas A. Cassini, Cathy Shyr

llms agents fine-tuning benchmarks

arXiv Machine Learning

Aug 18

One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail

arXiv:2608. 14683v1 Announce Type: new Abstract: Given a patient's clinical findings, a diagnostic system ranks possible diseases and must decide when to endorse its first prediction or defer it for review.

By Zhaoyang Jiang, Zhizhong Fu, Yunsoo Kim, Zicheng Li, Xuanqi Peng, Fei Teng, Jiacong Mi, Honghan Wu

llms

arXiv AI

Sep 1

SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence

arXiv:2608.29582v1 Announce Type: cross Abstract: Current evaluations of large language models (LLMs) primarily focus on factual knowledge retrieval, overlooking the fundamental challenge of navigati...

By Yi Yu, Bo Wang, Chong Feng, Ge Shi, Xia Liu, Ziyi Yang, Xuewen Shi

llms benchmarks safety

arXiv AI

Jul 2

RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotation

arXiv:2607. 00147v1 Announce Type: new Abstract: Rare disease differential diagnosis is a critical yet arduous clinical task, requiring physicians to identify precise phenotypes from complex, unstructured patient symptoms and execute intricate reasoning within a vast search space.

By Deyang Jiang, Haoran Wu, Ziyi Wang, Yiming Rong, Yunlong Zhao, Ye Jin, Bo Xu

llms rag agents reinforcement-learning benchmarks

arXiv AI

Jul 28

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs

arXiv:2607. 22555v1 Announce Type: new Abstract: Medical diagnosis is a multi-stage process: extract facts, consult knowledge, generate a differential analysis, and select the best diagnosis with explanations.

By Mahmood Bayeshi, Veysel Kocaman, Muhammed Ali Naqvi, Yigit Gul, David Talby

llms rag agents benchmarks

One email a morning, machine-written

Related stories

OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints?

LiteOdyssey: A Lightweight Reasoning AI Agent for Interpretable Rare-Disease Diagnosis

One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail

SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence

RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotation

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs