@inproceedings{zhang-etal-2026-tsa,
title = "{TSA}-{RAG}: Structure-Preserving Retrieval-Augmented Generation via Tiered Document Graph",
author = "Zhang, Kaiyuan and
Feng, Chong and
Shi, Ge and
Xu, Lingnan and
Wang, Bo",
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.754/",
pages = "15874--15894",
ISBN = "979-8-89176-462-0",
abstract = "Retrieval-Augmented Generation (RAG) effectively mitigates hallucinations and knowledge obsolescence in Large Language Models (LLMs). However, prevailing RAG systems typically retrieve evidence from discrete chunks or through decoupled structures, making it difficult to jointly preserve cross-document navigability and within-document coherence on complex tasks. To address this challenge, we propose TSA-RAG (Tiered-Structure-Aware RAG), a unified framework that recasts retrieval as structure-preserving navigation over a Tiered Document Graph (TDG). The TDG offers a joint retrieval space that explicitly couples relational topology with hierarchical skeletons, enabling seamless traversal across granularities. Building on this representation, TSA-RAG navigates evidence through a progressive Expand-Route-Retrieve paradigm, which expands query-focused subgraphs under path-consistency constraints, routes the query to structural entry points within relevant documents, and retrieves subtree-structured evidence preserving discourse continuity. Extensive experiments on seven QA datasets demonstrate that TSA-RAG consistently outperforms strong baselines while yielding more compact retrieval contexts. Quantitative analyses further confirm the scalability and robustness of our framework. Code is available at https://github.com/ZKYQUQ/TSA-RAG."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-tsa">
<titleInfo>
<title>TSA-RAG: Structure-Preserving Retrieval-Augmented Generation via Tiered Document Graph</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaiyuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ge</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingnan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Wang</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>Retrieval-Augmented Generation (RAG) effectively mitigates hallucinations and knowledge obsolescence in Large Language Models (LLMs). However, prevailing RAG systems typically retrieve evidence from discrete chunks or through decoupled structures, making it difficult to jointly preserve cross-document navigability and within-document coherence on complex tasks. To address this challenge, we propose TSA-RAG (Tiered-Structure-Aware RAG), a unified framework that recasts retrieval as structure-preserving navigation over a Tiered Document Graph (TDG). The TDG offers a joint retrieval space that explicitly couples relational topology with hierarchical skeletons, enabling seamless traversal across granularities. Building on this representation, TSA-RAG navigates evidence through a progressive Expand-Route-Retrieve paradigm, which expands query-focused subgraphs under path-consistency constraints, routes the query to structural entry points within relevant documents, and retrieves subtree-structured evidence preserving discourse continuity. Extensive experiments on seven QA datasets demonstrate that TSA-RAG consistently outperforms strong baselines while yielding more compact retrieval contexts. Quantitative analyses further confirm the scalability and robustness of our framework. Code is available at https://github.com/ZKYQUQ/TSA-RAG.</abstract>
<identifier type="citekey">zhang-etal-2026-tsa</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.754/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>15874</start>
<end>15894</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TSA-RAG: Structure-Preserving Retrieval-Augmented Generation via Tiered Document Graph
%A Zhang, Kaiyuan
%A Feng, Chong
%A Shi, Ge
%A Xu, Lingnan
%A Wang, Bo
%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 zhang-etal-2026-tsa
%X Retrieval-Augmented Generation (RAG) effectively mitigates hallucinations and knowledge obsolescence in Large Language Models (LLMs). However, prevailing RAG systems typically retrieve evidence from discrete chunks or through decoupled structures, making it difficult to jointly preserve cross-document navigability and within-document coherence on complex tasks. To address this challenge, we propose TSA-RAG (Tiered-Structure-Aware RAG), a unified framework that recasts retrieval as structure-preserving navigation over a Tiered Document Graph (TDG). The TDG offers a joint retrieval space that explicitly couples relational topology with hierarchical skeletons, enabling seamless traversal across granularities. Building on this representation, TSA-RAG navigates evidence through a progressive Expand-Route-Retrieve paradigm, which expands query-focused subgraphs under path-consistency constraints, routes the query to structural entry points within relevant documents, and retrieves subtree-structured evidence preserving discourse continuity. Extensive experiments on seven QA datasets demonstrate that TSA-RAG consistently outperforms strong baselines while yielding more compact retrieval contexts. Quantitative analyses further confirm the scalability and robustness of our framework. Code is available at https://github.com/ZKYQUQ/TSA-RAG.
%U https://aclanthology.org/2026.findings-emnlp.754/
%P 15874-15894
Markdown (Informal)
[TSA-RAG: Structure-Preserving Retrieval-Augmented Generation via Tiered Document Graph](https://aclanthology.org/2026.findings-emnlp.754/) (Zhang et al., Findings 2026)
ACL