@inproceedings{wang-etal-2026-totofilter,
title = "{T}o{T}o{F}ilter: Topic- and Topology-Aware Noise Filtering Framework over Medical {KG}s for Evidence-Based Medical {Q}{\&}{A}",
author = "Wang, Yufeng and
Chen, Weijie and
Chen, Chao and
Liu, Xingfeng and
Yang, Yizhe and
Chen, Zhihao and
He, Qiming and
Chen, Yubo and
Liu, Kang and
Wang, Xuefeng and
Liao, Xiangwen and
Liu, Jingfeng",
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.1349/",
pages = "30750--30770",
ISBN = "979-8-89176-459-0",
abstract = "Evidence-Based Medical Question Answering (EB-MQA) aims to provide accurate and verifiable responses to support clinical decisions. To retrieve evidence from general medical knowledge graphs (KGs), existing knowledge augmentation methods use semantic similarity or dynamic sampling for entity matching and agentic expansion or subgraph scoring for path retrieval. These approaches can introduce entity-level noise from irrelevant or generic entities and path-level noise from redundant or spurious reasoning chains. We propose ToToFilter, a train-free topic- and topology-aware noise filtering framework with Topic-Aware Entity Localization for query-relevant entity anchoring and Topology-Aware Path Filtering for path selection based on semantic consistency, structural compactness, and information specificity. Across four MQA benchmarks, ToToFilter achieves average accuracy gains of 2.30 and 1.22 percentage points over DALK on Llama3.1-8B and Qwen2.5-7B, with maximum gains of 2.60 and 2.78 points. On PrimeKGQA, it improves answer recall and triple recall by up to 8.81 and 19.70 percentage points. Further analyses verify the effectiveness of the proposed two-level filtering framework."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-totofilter">
<titleInfo>
<title>ToToFilter: Topic- and Topology-Aware Noise Filtering Framework over Medical KGs for Evidence-Based Medical Q&A</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingfeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yizhe</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiming</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuefeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangwen</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingfeng</namePart>
<namePart type="family">Liu</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>Evidence-Based Medical Question Answering (EB-MQA) aims to provide accurate and verifiable responses to support clinical decisions. To retrieve evidence from general medical knowledge graphs (KGs), existing knowledge augmentation methods use semantic similarity or dynamic sampling for entity matching and agentic expansion or subgraph scoring for path retrieval. These approaches can introduce entity-level noise from irrelevant or generic entities and path-level noise from redundant or spurious reasoning chains. We propose ToToFilter, a train-free topic- and topology-aware noise filtering framework with Topic-Aware Entity Localization for query-relevant entity anchoring and Topology-Aware Path Filtering for path selection based on semantic consistency, structural compactness, and information specificity. Across four MQA benchmarks, ToToFilter achieves average accuracy gains of 2.30 and 1.22 percentage points over DALK on Llama3.1-8B and Qwen2.5-7B, with maximum gains of 2.60 and 2.78 points. On PrimeKGQA, it improves answer recall and triple recall by up to 8.81 and 19.70 percentage points. Further analyses verify the effectiveness of the proposed two-level filtering framework.</abstract>
<identifier type="citekey">wang-etal-2026-totofilter</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1349/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>30750</start>
<end>30770</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ToToFilter: Topic- and Topology-Aware Noise Filtering Framework over Medical KGs for Evidence-Based Medical Q&A
%A Wang, Yufeng
%A Chen, Weijie
%A Chen, Chao
%A Liu, Xingfeng
%A Yang, Yizhe
%A Chen, Zhihao
%A He, Qiming
%A Chen, Yubo
%A Liu, Kang
%A Wang, Xuefeng
%A Liao, Xiangwen
%A Liu, Jingfeng
%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-totofilter
%X Evidence-Based Medical Question Answering (EB-MQA) aims to provide accurate and verifiable responses to support clinical decisions. To retrieve evidence from general medical knowledge graphs (KGs), existing knowledge augmentation methods use semantic similarity or dynamic sampling for entity matching and agentic expansion or subgraph scoring for path retrieval. These approaches can introduce entity-level noise from irrelevant or generic entities and path-level noise from redundant or spurious reasoning chains. We propose ToToFilter, a train-free topic- and topology-aware noise filtering framework with Topic-Aware Entity Localization for query-relevant entity anchoring and Topology-Aware Path Filtering for path selection based on semantic consistency, structural compactness, and information specificity. Across four MQA benchmarks, ToToFilter achieves average accuracy gains of 2.30 and 1.22 percentage points over DALK on Llama3.1-8B and Qwen2.5-7B, with maximum gains of 2.60 and 2.78 points. On PrimeKGQA, it improves answer recall and triple recall by up to 8.81 and 19.70 percentage points. Further analyses verify the effectiveness of the proposed two-level filtering framework.
%U https://aclanthology.org/2026.emnlp-main.1349/
%P 30750-30770
Markdown (Informal)
[ToToFilter: Topic- and Topology-Aware Noise Filtering Framework over Medical KGs for Evidence-Based Medical Q&A](https://aclanthology.org/2026.emnlp-main.1349/) (Wang et al., EMNLP 2026)
ACL
- Yufeng Wang, Weijie Chen, Chao Chen, Xingfeng Liu, Yizhe Yang, Zhihao Chen, Qiming He, Yubo Chen, Kang Liu, Xuefeng Wang, Xiangwen Liao, and Jingfeng Liu. 2026. ToToFilter: Topic- and Topology-Aware Noise Filtering Framework over Medical KGs for Evidence-Based Medical Q&A. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 30750–30770, Budapest, Hungary. Association for Computational Linguistics.