@inproceedings{shi-etal-2026-concept,
title = "Concept rather than Document: Context Compression via {AMR}-based Conceptual Entropy",
author = "Shi, Kaize and
Sun, Xueyao and
Tao, Xiaohui and
Li, Lin and
Lin, Qika and
Xu, Guandong",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.590/",
pages = "12158--12173",
ISBN = "979-8-89176-395-1",
abstract = "Large Language Models (LLMs) face information overload when handling long contexts, particularly in Retrieval-Augmented Generation (RAG) where extensive supporting documents introduce redundant content that interferes with reasoning. Context engineering has emerged to address these challenges, yet existing methods rely on lexical or token-level features that fragment semantic units and fail to capture conceptually essential content. We propose an unsupervised context compression framework leveraging Abstract Meaning Representation (AMR) to preserve semantically essential information while filtering irrelevant text. By quantifying node-level entropy within AMR graphs, our method estimates the conceptual importance of each node, enabling retention of core semantics. Specifically, we construct AMR graphs from retrieved contexts, compute the conceptual entropy of each node, and identify statistically significant concepts to form a condensed, semantically focused context. Experiments on the PopQA and EntityQuestions datasets demonstrate that our method outperforms vanilla RAG and existing baselines, achieving superior accuracy while substantially reducing context length. To the best of our knowledge, this is the first work introducing AMR-based conceptual entropy for context compression, demonstrating the potential of structured linguistic representations in context engineering."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2026-concept">
<titleInfo>
<title>Concept rather than Document: Context Compression via AMR-based Conceptual Entropy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaize</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueyao</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohui</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qika</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guandong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) face information overload when handling long contexts, particularly in Retrieval-Augmented Generation (RAG) where extensive supporting documents introduce redundant content that interferes with reasoning. Context engineering has emerged to address these challenges, yet existing methods rely on lexical or token-level features that fragment semantic units and fail to capture conceptually essential content. We propose an unsupervised context compression framework leveraging Abstract Meaning Representation (AMR) to preserve semantically essential information while filtering irrelevant text. By quantifying node-level entropy within AMR graphs, our method estimates the conceptual importance of each node, enabling retention of core semantics. Specifically, we construct AMR graphs from retrieved contexts, compute the conceptual entropy of each node, and identify statistically significant concepts to form a condensed, semantically focused context. Experiments on the PopQA and EntityQuestions datasets demonstrate that our method outperforms vanilla RAG and existing baselines, achieving superior accuracy while substantially reducing context length. To the best of our knowledge, this is the first work introducing AMR-based conceptual entropy for context compression, demonstrating the potential of structured linguistic representations in context engineering.</abstract>
<identifier type="citekey">shi-etal-2026-concept</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.590/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>12158</start>
<end>12173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Concept rather than Document: Context Compression via AMR-based Conceptual Entropy
%A Shi, Kaize
%A Sun, Xueyao
%A Tao, Xiaohui
%A Li, Lin
%A Lin, Qika
%A Xu, Guandong
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F shi-etal-2026-concept
%X Large Language Models (LLMs) face information overload when handling long contexts, particularly in Retrieval-Augmented Generation (RAG) where extensive supporting documents introduce redundant content that interferes with reasoning. Context engineering has emerged to address these challenges, yet existing methods rely on lexical or token-level features that fragment semantic units and fail to capture conceptually essential content. We propose an unsupervised context compression framework leveraging Abstract Meaning Representation (AMR) to preserve semantically essential information while filtering irrelevant text. By quantifying node-level entropy within AMR graphs, our method estimates the conceptual importance of each node, enabling retention of core semantics. Specifically, we construct AMR graphs from retrieved contexts, compute the conceptual entropy of each node, and identify statistically significant concepts to form a condensed, semantically focused context. Experiments on the PopQA and EntityQuestions datasets demonstrate that our method outperforms vanilla RAG and existing baselines, achieving superior accuracy while substantially reducing context length. To the best of our knowledge, this is the first work introducing AMR-based conceptual entropy for context compression, demonstrating the potential of structured linguistic representations in context engineering.
%U https://aclanthology.org/2026.findings-acl.590/
%P 12158-12173
Markdown (Informal)
[Concept rather than Document: Context Compression via AMR-based Conceptual Entropy](https://aclanthology.org/2026.findings-acl.590/) (Shi et al., Findings 2026)
ACL