@inproceedings{zhou-etal-2026-orbit,
title = "{ORBIT}: Traceable Rare-Disease Diagnosis via Orphanet-Grounded Retrieval and Bounded {LLM} Interaction",
author = "Zhou, Songchi and
Chen, Haichao and
Yu, Sheng",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.358/",
pages = "7497--7514",
ISBN = "979-8-89176-462-0",
abstract = "Rare-disease diagnosis requires converting heterogeneous patient descriptions into a ranked differential over thousands of disorders while keeping each hypothesis tied to verifiable evidence. Phenotype-based tools provide structured, interpretable comparisons but usually require normalized Human Phenotype Ontology (HPO) input. Large language models (LLMs) can read clinical narratives and propose broader hypotheses, yet their free-form outputs are difficult to ground in a disease catalog or combine with ontology-based evidence. We present ORBIT (Orphanet-grounded Retrieval and Bounded LLM Interaction for Traceable rare-disease diagnosis), a catalog-grounded diagnosis layer for both free-text and structured-HPO cases. ORBIT grounds open disease proposals to Orphanet, fuses them with exact phenotype and case-profile retrieval, scores only the resulting candidate pool with a probabilistic model, and reranks a fixed menu of evidence-bearing disease cards. The output records catalog identifiers, candidate provenance, phenotype support, and conflicts. Across RareArena and RareBench, ORBIT improves every reported metric over single-agent and medical-agent systems using the same backbone. Retrieval analysis, ablations, and expert review further identify where complementary candidate sources, iterative refinement, and constrained reranking affect performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2026-orbit">
<titleInfo>
<title>ORBIT: Traceable Rare-Disease Diagnosis via Orphanet-Grounded Retrieval and Bounded LLM Interaction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Songchi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haichao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Rare-disease diagnosis requires converting heterogeneous patient descriptions into a ranked differential over thousands of disorders while keeping each hypothesis tied to verifiable evidence. Phenotype-based tools provide structured, interpretable comparisons but usually require normalized Human Phenotype Ontology (HPO) input. Large language models (LLMs) can read clinical narratives and propose broader hypotheses, yet their free-form outputs are difficult to ground in a disease catalog or combine with ontology-based evidence. We present ORBIT (Orphanet-grounded Retrieval and Bounded LLM Interaction for Traceable rare-disease diagnosis), a catalog-grounded diagnosis layer for both free-text and structured-HPO cases. ORBIT grounds open disease proposals to Orphanet, fuses them with exact phenotype and case-profile retrieval, scores only the resulting candidate pool with a probabilistic model, and reranks a fixed menu of evidence-bearing disease cards. The output records catalog identifiers, candidate provenance, phenotype support, and conflicts. Across RareArena and RareBench, ORBIT improves every reported metric over single-agent and medical-agent systems using the same backbone. Retrieval analysis, ablations, and expert review further identify where complementary candidate sources, iterative refinement, and constrained reranking affect performance.</abstract>
<identifier type="citekey">zhou-etal-2026-orbit</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.358/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>7497</start>
<end>7514</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ORBIT: Traceable Rare-Disease Diagnosis via Orphanet-Grounded Retrieval and Bounded LLM Interaction
%A Zhou, Songchi
%A Chen, Haichao
%A Yu, Sheng
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zhou-etal-2026-orbit
%X Rare-disease diagnosis requires converting heterogeneous patient descriptions into a ranked differential over thousands of disorders while keeping each hypothesis tied to verifiable evidence. Phenotype-based tools provide structured, interpretable comparisons but usually require normalized Human Phenotype Ontology (HPO) input. Large language models (LLMs) can read clinical narratives and propose broader hypotheses, yet their free-form outputs are difficult to ground in a disease catalog or combine with ontology-based evidence. We present ORBIT (Orphanet-grounded Retrieval and Bounded LLM Interaction for Traceable rare-disease diagnosis), a catalog-grounded diagnosis layer for both free-text and structured-HPO cases. ORBIT grounds open disease proposals to Orphanet, fuses them with exact phenotype and case-profile retrieval, scores only the resulting candidate pool with a probabilistic model, and reranks a fixed menu of evidence-bearing disease cards. The output records catalog identifiers, candidate provenance, phenotype support, and conflicts. Across RareArena and RareBench, ORBIT improves every reported metric over single-agent and medical-agent systems using the same backbone. Retrieval analysis, ablations, and expert review further identify where complementary candidate sources, iterative refinement, and constrained reranking affect performance.
%U https://aclanthology.org/2026.findings-emnlp.358/
%P 7497-7514
Markdown (Informal)
[ORBIT: Traceable Rare-Disease Diagnosis via Orphanet-Grounded Retrieval and Bounded LLM Interaction](https://aclanthology.org/2026.findings-emnlp.358/) (Zhou et al., Findings 2026)
ACL