@inproceedings{chernyavskiy-etal-2026-discorag,
title = "{D}isco{RAG}: A Discourse-Aware Agent for Query-Based Summarization of Long Documents",
author = "Chernyavskiy, Alexander and
Ostyakova, Lidiia and
Ilvovsky, Dmitry",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.162/",
doi = "10.63317/2u9sjkc357ro",
pages = "2062--2075",
abstract = "Query-based summarization of long documents is often tackled with retrieval-augmented generation (RAG). However, conventional RAG models exhibit limitations when applied to narrative texts, where crucial evidence is often implicit and distributed. This exposes a distinct class of ``discourse-aware'' queries that require specialized, structure-aware models. To address this, we introduce DiscoRAG, a framework that leverages Rhetorical Structure Theory (RST). By modeling the document as a discourse tree, DiscoRAG navigates its structure, explicitly using rhetorical relations to focus on and aggregate evidence from globally related segments. Furthermore, our pipeline integrates a classifier that assesses query complexity to dynamically select the most efficient retrieval strategy. We evaluate our DiscoRAG against standard and extended-context RAG pipelines on the SQuALITY dataset, which we release augmented with questions requiring deep discourse reasoning and integration of the global narrative. Our results demonstrate that this method sizeably outperforms these baselines, demonstrating its superior ability to assemble a coherent, contextually rich evidence base by interpreting the global narrative structure rather than relying on local semantic similarity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chernyavskiy-etal-2026-discorag">
<titleInfo>
<title>DiscoRAG: A Discourse-Aware Agent for Query-Based Summarization of Long Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Chernyavskiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidiia</namePart>
<namePart type="family">Ostyakova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ilvovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Query-based summarization of long documents is often tackled with retrieval-augmented generation (RAG). However, conventional RAG models exhibit limitations when applied to narrative texts, where crucial evidence is often implicit and distributed. This exposes a distinct class of “discourse-aware” queries that require specialized, structure-aware models. To address this, we introduce DiscoRAG, a framework that leverages Rhetorical Structure Theory (RST). By modeling the document as a discourse tree, DiscoRAG navigates its structure, explicitly using rhetorical relations to focus on and aggregate evidence from globally related segments. Furthermore, our pipeline integrates a classifier that assesses query complexity to dynamically select the most efficient retrieval strategy. We evaluate our DiscoRAG against standard and extended-context RAG pipelines on the SQuALITY dataset, which we release augmented with questions requiring deep discourse reasoning and integration of the global narrative. Our results demonstrate that this method sizeably outperforms these baselines, demonstrating its superior ability to assemble a coherent, contextually rich evidence base by interpreting the global narrative structure rather than relying on local semantic similarity.</abstract>
<identifier type="citekey">chernyavskiy-etal-2026-discorag</identifier>
<identifier type="doi">10.63317/2u9sjkc357ro</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.162/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2062</start>
<end>2075</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiscoRAG: A Discourse-Aware Agent for Query-Based Summarization of Long Documents
%A Chernyavskiy, Alexander
%A Ostyakova, Lidiia
%A Ilvovsky, Dmitry
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F chernyavskiy-etal-2026-discorag
%X Query-based summarization of long documents is often tackled with retrieval-augmented generation (RAG). However, conventional RAG models exhibit limitations when applied to narrative texts, where crucial evidence is often implicit and distributed. This exposes a distinct class of “discourse-aware” queries that require specialized, structure-aware models. To address this, we introduce DiscoRAG, a framework that leverages Rhetorical Structure Theory (RST). By modeling the document as a discourse tree, DiscoRAG navigates its structure, explicitly using rhetorical relations to focus on and aggregate evidence from globally related segments. Furthermore, our pipeline integrates a classifier that assesses query complexity to dynamically select the most efficient retrieval strategy. We evaluate our DiscoRAG against standard and extended-context RAG pipelines on the SQuALITY dataset, which we release augmented with questions requiring deep discourse reasoning and integration of the global narrative. Our results demonstrate that this method sizeably outperforms these baselines, demonstrating its superior ability to assemble a coherent, contextually rich evidence base by interpreting the global narrative structure rather than relying on local semantic similarity.
%R 10.63317/2u9sjkc357ro
%U https://aclanthology.org/2026.lrec-1.162/
%U https://doi.org/10.63317/2u9sjkc357ro
%P 2062-2075
Markdown (Informal)
[DiscoRAG: A Discourse-Aware Agent for Query-Based Summarization of Long Documents](https://aclanthology.org/2026.lrec-1.162/) (Chernyavskiy et al., LREC 2026)
ACL