@inproceedings{li-etal-2026-near,
title = "{NEAR}: Neighborhood-Aware Context Reconstruction for Ultra-Long Document Reading Comprehension of {LLM}s",
author = "Li, Han and
Chen, Xuanang and
He, Ben and
Sun, Le",
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.886/",
pages = "20434--20453",
ISBN = "979-8-89176-459-0",
abstract = "Large language models (LLMs) remain challenged by ultra-long document understanding. A common solution is to segment documents into chunks and retrieve those relevant to a query, but this can disrupt semantic and logical coherence by ignoring dependencies between chunks. We propose NEAR (NEighborhood-Aware context Reconstruction), a lightweight, training-free framework that reconstructs coherent context from fragmented segments. NEAR represents each document as a dual-layer neighborhood graph, connecting chunks via topical neighbors to capture long-range semantic relations and physical neighbors to preserve local continuity. An iterative dual-pool exploration traverses chunks from both global and local neighborhoods, and collected chunks are selectively expanded and reordered according to their original positions to form a coherent input context. Extensive experiments on multiple long-document question answering benchmarks demonstrate that NEAR improves comprehension performance while maintaining low latency and memory usage."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-near">
<titleInfo>
<title>NEAR: Neighborhood-Aware Context Reconstruction for Ultra-Long Document Reading Comprehension of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Sun</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>Large language models (LLMs) remain challenged by ultra-long document understanding. A common solution is to segment documents into chunks and retrieve those relevant to a query, but this can disrupt semantic and logical coherence by ignoring dependencies between chunks. We propose NEAR (NEighborhood-Aware context Reconstruction), a lightweight, training-free framework that reconstructs coherent context from fragmented segments. NEAR represents each document as a dual-layer neighborhood graph, connecting chunks via topical neighbors to capture long-range semantic relations and physical neighbors to preserve local continuity. An iterative dual-pool exploration traverses chunks from both global and local neighborhoods, and collected chunks are selectively expanded and reordered according to their original positions to form a coherent input context. Extensive experiments on multiple long-document question answering benchmarks demonstrate that NEAR improves comprehension performance while maintaining low latency and memory usage.</abstract>
<identifier type="citekey">li-etal-2026-near</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.886/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>20434</start>
<end>20453</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NEAR: Neighborhood-Aware Context Reconstruction for Ultra-Long Document Reading Comprehension of LLMs
%A Li, Han
%A Chen, Xuanang
%A He, Ben
%A Sun, Le
%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 li-etal-2026-near
%X Large language models (LLMs) remain challenged by ultra-long document understanding. A common solution is to segment documents into chunks and retrieve those relevant to a query, but this can disrupt semantic and logical coherence by ignoring dependencies between chunks. We propose NEAR (NEighborhood-Aware context Reconstruction), a lightweight, training-free framework that reconstructs coherent context from fragmented segments. NEAR represents each document as a dual-layer neighborhood graph, connecting chunks via topical neighbors to capture long-range semantic relations and physical neighbors to preserve local continuity. An iterative dual-pool exploration traverses chunks from both global and local neighborhoods, and collected chunks are selectively expanded and reordered according to their original positions to form a coherent input context. Extensive experiments on multiple long-document question answering benchmarks demonstrate that NEAR improves comprehension performance while maintaining low latency and memory usage.
%U https://aclanthology.org/2026.emnlp-main.886/
%P 20434-20453
Markdown (Informal)
[NEAR: Neighborhood-Aware Context Reconstruction for Ultra-Long Document Reading Comprehension of LLMs](https://aclanthology.org/2026.emnlp-main.886/) (Li et al., EMNLP 2026)
ACL