@inproceedings{nishida-etal-2026-beyond,
title = "Beyond Retrieval: Structuring Evolving and Inconsistent External Knowledge with Proposition Relations for {RAG}",
author = "Nishida, Noriki and
Cheng, Fei and
Matsumoto, Yuji",
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.294/",
pages = "6749--6771",
ISBN = "979-8-89176-459-0",
abstract = "Real-world knowledge bases evolve over time and accumulate outdated statements, contradictions, and misinformation. LLMs have been reported to be vulnerable to such inconsistent contexts. In this paper, we propose Proposition-Structured RAG (ProStruct-RAG), a framework that continuously structures evolving and inconsistent external knowledge bases using timestamped propositions and inter-proposition relations. ProStruct-RAG represents a document collection as a graph whose nodes are propositions and whose edges capture temporal updates, contradictions, and support relations, retrieves query-relevant knowledge as a relational structure, and uses it for answer generation in RAG. Experiments on multiple open-book temporal QA benchmarks show that ProStruct-RAG outperforms baselines that do not use inter-proposition relations, suggesting that RAG over evolving and inconsistent knowledge benefits from organizing external knowledge before retrieval, rather than relying solely on inference-time reasoning. We release our code and Asteria, a new fictional temporal QA dataset designed to mitigate data contamination."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishida-etal-2026-beyond">
<titleInfo>
<title>Beyond Retrieval: Structuring Evolving and Inconsistent External Knowledge with Proposition Relations for RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noriki</namePart>
<namePart type="family">Nishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</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>Real-world knowledge bases evolve over time and accumulate outdated statements, contradictions, and misinformation. LLMs have been reported to be vulnerable to such inconsistent contexts. In this paper, we propose Proposition-Structured RAG (ProStruct-RAG), a framework that continuously structures evolving and inconsistent external knowledge bases using timestamped propositions and inter-proposition relations. ProStruct-RAG represents a document collection as a graph whose nodes are propositions and whose edges capture temporal updates, contradictions, and support relations, retrieves query-relevant knowledge as a relational structure, and uses it for answer generation in RAG. Experiments on multiple open-book temporal QA benchmarks show that ProStruct-RAG outperforms baselines that do not use inter-proposition relations, suggesting that RAG over evolving and inconsistent knowledge benefits from organizing external knowledge before retrieval, rather than relying solely on inference-time reasoning. We release our code and Asteria, a new fictional temporal QA dataset designed to mitigate data contamination.</abstract>
<identifier type="citekey">nishida-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.294/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>6749</start>
<end>6771</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Retrieval: Structuring Evolving and Inconsistent External Knowledge with Proposition Relations for RAG
%A Nishida, Noriki
%A Cheng, Fei
%A Matsumoto, Yuji
%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 nishida-etal-2026-beyond
%X Real-world knowledge bases evolve over time and accumulate outdated statements, contradictions, and misinformation. LLMs have been reported to be vulnerable to such inconsistent contexts. In this paper, we propose Proposition-Structured RAG (ProStruct-RAG), a framework that continuously structures evolving and inconsistent external knowledge bases using timestamped propositions and inter-proposition relations. ProStruct-RAG represents a document collection as a graph whose nodes are propositions and whose edges capture temporal updates, contradictions, and support relations, retrieves query-relevant knowledge as a relational structure, and uses it for answer generation in RAG. Experiments on multiple open-book temporal QA benchmarks show that ProStruct-RAG outperforms baselines that do not use inter-proposition relations, suggesting that RAG over evolving and inconsistent knowledge benefits from organizing external knowledge before retrieval, rather than relying solely on inference-time reasoning. We release our code and Asteria, a new fictional temporal QA dataset designed to mitigate data contamination.
%U https://aclanthology.org/2026.emnlp-main.294/
%P 6749-6771
Markdown (Informal)
[Beyond Retrieval: Structuring Evolving and Inconsistent External Knowledge with Proposition Relations for RAG](https://aclanthology.org/2026.emnlp-main.294/) (Nishida et al., EMNLP 2026)
ACL