@inproceedings{wang-etal-2026-medical,
title = "Medical Bilingualism: Cross-Ontology Graph Retrieval for Incommensurable Knowledge Bases",
author = "Wang, Zixuan and
Lu, Ke and
Wang, Zihan and
Lei, Junwei and
Dong, Junhao and
Guo, Jinyu and
Chen, Chaomeng",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.201/",
pages = "4591--4612",
ISBN = "979-8-89176-459-0",
abstract = "Graph-based Retrieval-Augmented Generation (GraphRAG) can fail in interdisciplinary medicine where evidence comes from incommensurable knowledge systems, e.g., Traditional Chinese Medicine (TCM) and Western Medicine (WM). Similarity-driven retrieval in a shared latent space may over-unify heterogeneous concepts, causing semantic collapse (spurious alignments, provenance-blind mixing, and broken multi-hop chains). We propose Xonto-RAG, a cross-ontology GraphRAG framework that avoids ontological unification by constructing a dual-ontology graph with typed bridges induced via LLM-assisted verify-and-vote. A query-aware Relational Graph Attention Network (RGAT) then assembles compact, provenance-tracked multi-hop evidence subgraphs for grounded generation. Across TCM{--}WM benchmarks, Xonto-RAG outperforms strong RAG/GraphRAG baselines, seeing up to +22.2{\%} accuracy on MLEC-QA TCWM (vs. OG-RAG), 77.0{\%} accuracy with a 7B backbone, and 85.1{\%} faithfulness on MLEC-TCM, while reducing semantic-collapse failures and yielding interpretable reasoning chains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-medical">
<titleInfo>
<title>Medical Bilingualism: Cross-Ontology Graph Retrieval for Incommensurable Knowledge Bases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zixuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junwei</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhao</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinyu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaomeng</namePart>
<namePart type="family">Chen</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Graph-based Retrieval-Augmented Generation (GraphRAG) can fail in interdisciplinary medicine where evidence comes from incommensurable knowledge systems, e.g., Traditional Chinese Medicine (TCM) and Western Medicine (WM). Similarity-driven retrieval in a shared latent space may over-unify heterogeneous concepts, causing semantic collapse (spurious alignments, provenance-blind mixing, and broken multi-hop chains). We propose Xonto-RAG, a cross-ontology GraphRAG framework that avoids ontological unification by constructing a dual-ontology graph with typed bridges induced via LLM-assisted verify-and-vote. A query-aware Relational Graph Attention Network (RGAT) then assembles compact, provenance-tracked multi-hop evidence subgraphs for grounded generation. Across TCM–WM benchmarks, Xonto-RAG outperforms strong RAG/GraphRAG baselines, seeing up to +22.2% accuracy on MLEC-QA TCWM (vs. OG-RAG), 77.0% accuracy with a 7B backbone, and 85.1% faithfulness on MLEC-TCM, while reducing semantic-collapse failures and yielding interpretable reasoning chains.</abstract>
<identifier type="citekey">wang-etal-2026-medical</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.201/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>4591</start>
<end>4612</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Medical Bilingualism: Cross-Ontology Graph Retrieval for Incommensurable Knowledge Bases
%A Wang, Zixuan
%A Lu, Ke
%A Wang, Zihan
%A Lei, Junwei
%A Dong, Junhao
%A Guo, Jinyu
%A Chen, Chaomeng
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wang-etal-2026-medical
%X Graph-based Retrieval-Augmented Generation (GraphRAG) can fail in interdisciplinary medicine where evidence comes from incommensurable knowledge systems, e.g., Traditional Chinese Medicine (TCM) and Western Medicine (WM). Similarity-driven retrieval in a shared latent space may over-unify heterogeneous concepts, causing semantic collapse (spurious alignments, provenance-blind mixing, and broken multi-hop chains). We propose Xonto-RAG, a cross-ontology GraphRAG framework that avoids ontological unification by constructing a dual-ontology graph with typed bridges induced via LLM-assisted verify-and-vote. A query-aware Relational Graph Attention Network (RGAT) then assembles compact, provenance-tracked multi-hop evidence subgraphs for grounded generation. Across TCM–WM benchmarks, Xonto-RAG outperforms strong RAG/GraphRAG baselines, seeing up to +22.2% accuracy on MLEC-QA TCWM (vs. OG-RAG), 77.0% accuracy with a 7B backbone, and 85.1% faithfulness on MLEC-TCM, while reducing semantic-collapse failures and yielding interpretable reasoning chains.
%U https://aclanthology.org/2026.emnlp-main.201/
%P 4591-4612
Markdown (Informal)
[Medical Bilingualism: Cross-Ontology Graph Retrieval for Incommensurable Knowledge Bases](https://aclanthology.org/2026.emnlp-main.201/) (Wang et al., EMNLP 2026)
ACL