@inproceedings{achkar-etal-2026-cost,
title = "The Cost of Decomposition: Trade-Offs in Long-Context Aspect-Based Scientific Summarization",
author = "Achkar, Pierre and
Senger, Elena and
Gollub, Tim and
Potthast, Martin and
Campbell, Yuri",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.95/",
pages = "1613--1636",
ISBN = "979-8-89176-460-6",
abstract = "Aspect-based scientific summarization produces a focused summary of a long document for a given aspect (e.g., Approach, Methods). Prior work decomposes the task, assuming a model can neither attend over the full document nor resolve aspect complexity in one pass. We revisit both assumptions now that compact yet capable language models handle long contexts natively. Across three datasets and two primary open long-context models, decomposition provides no reliable quality advantage over direct full-document prompting. With the main 9B model, zero-shot is strongest on aggregate lexical, semantic, and claim-recall/F1 metrics; under the 7B robustness model, simple decomposed variants occasionally edge zero-shot, but gains are small and inconsistent. On these primary models, the multi-role agentic pipeline is never best in aggregate and incurs substantially higher token cost, whereas RAG uses roughly one seventh of zero-shot{'}s tokens but delivers lower, less consistent quality. We characterize where added complexity loses, quantify the cost{--}quality trade-off, and distill practical deployment guidance. Code is available on GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="achkar-etal-2026-cost">
<titleInfo>
<title>The Cost of Decomposition: Trade-Offs in Long-Context Aspect-Based Scientific Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Achkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Senger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Gollub</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Potthast</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Campbell</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: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Aspect-based scientific summarization produces a focused summary of a long document for a given aspect (e.g., Approach, Methods). Prior work decomposes the task, assuming a model can neither attend over the full document nor resolve aspect complexity in one pass. We revisit both assumptions now that compact yet capable language models handle long contexts natively. Across three datasets and two primary open long-context models, decomposition provides no reliable quality advantage over direct full-document prompting. With the main 9B model, zero-shot is strongest on aggregate lexical, semantic, and claim-recall/F1 metrics; under the 7B robustness model, simple decomposed variants occasionally edge zero-shot, but gains are small and inconsistent. On these primary models, the multi-role agentic pipeline is never best in aggregate and incurs substantially higher token cost, whereas RAG uses roughly one seventh of zero-shot’s tokens but delivers lower, less consistent quality. We characterize where added complexity loses, quantify the cost–quality trade-off, and distill practical deployment guidance. Code is available on GitHub.</abstract>
<identifier type="citekey">achkar-etal-2026-cost</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.95/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1613</start>
<end>1636</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Cost of Decomposition: Trade-Offs in Long-Context Aspect-Based Scientific Summarization
%A Achkar, Pierre
%A Senger, Elena
%A Gollub, Tim
%A Potthast, Martin
%A Campbell, Yuri
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F achkar-etal-2026-cost
%X Aspect-based scientific summarization produces a focused summary of a long document for a given aspect (e.g., Approach, Methods). Prior work decomposes the task, assuming a model can neither attend over the full document nor resolve aspect complexity in one pass. We revisit both assumptions now that compact yet capable language models handle long contexts natively. Across three datasets and two primary open long-context models, decomposition provides no reliable quality advantage over direct full-document prompting. With the main 9B model, zero-shot is strongest on aggregate lexical, semantic, and claim-recall/F1 metrics; under the 7B robustness model, simple decomposed variants occasionally edge zero-shot, but gains are small and inconsistent. On these primary models, the multi-role agentic pipeline is never best in aggregate and incurs substantially higher token cost, whereas RAG uses roughly one seventh of zero-shot’s tokens but delivers lower, less consistent quality. We characterize where added complexity loses, quantify the cost–quality trade-off, and distill practical deployment guidance. Code is available on GitHub.
%U https://aclanthology.org/2026.emnlp-industry.95/
%P 1613-1636
Markdown (Informal)
[The Cost of Decomposition: Trade-Offs in Long-Context Aspect-Based Scientific Summarization](https://aclanthology.org/2026.emnlp-industry.95/) (Achkar et al., EMNLP 2026)
ACL