@inproceedings{zhou-etal-2026-aed,
title = "{AED}-{RAG}: Continuous Multi-Granular Context Fusion for Retrieval-Augmented Generation via Adaptive Ensemble Decoding",
author = "Zhou, Junzhe and
Lin, Fulin and
Cheng, Tairan and
Chen, Shaowen and
Wang, Hongwei",
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.1148/",
pages = "22885--22899",
ISBN = "979-8-89176-395-1",
abstract = "Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) yet suffers from a mismatch between coarse retrieval granularity and fine-grained generation needs. Specifically, coarse-grained passages inherently conflate valid context with intra-passage noise that semantic retrieval often fails to filter. Existing alignment strategies, typically relying on discrete reranking, struggle to address this granularity mismatch or effectively balance external evidence with internal knowledge. To bridge this gap, we propose **AED-RAG**, a framework that synergizes discrete retrieval with continuous **A**daptive **E**nsemble **D**ecoding. Specifically, we fine-tune a utility predictor using contrastive perplexity to discern the information density differences between unstructured narrative passages and structured knowledge triplets. During inference, this predictor projects passages, triplets, and the model{'}s parametric memory into a unified probability space, enabling a soft, token-level fusion that dynamically optimizes information gain. Extensive experiments on four open-domain QA benchmarks demonstrate that AED-RAG significantly outperforms competitive baselines, underscoring the effectiveness of integrating multi-granular contexts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2026-aed">
<titleInfo>
<title>AED-RAG: Continuous Multi-Granular Context Fusion for Retrieval-Augmented Generation via Adaptive Ensemble Decoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junzhe</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fulin</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tairan</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaowen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongwei</namePart>
<namePart type="family">Wang</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>Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) yet suffers from a mismatch between coarse retrieval granularity and fine-grained generation needs. Specifically, coarse-grained passages inherently conflate valid context with intra-passage noise that semantic retrieval often fails to filter. Existing alignment strategies, typically relying on discrete reranking, struggle to address this granularity mismatch or effectively balance external evidence with internal knowledge. To bridge this gap, we propose **AED-RAG**, a framework that synergizes discrete retrieval with continuous **A**daptive **E**nsemble **D**ecoding. Specifically, we fine-tune a utility predictor using contrastive perplexity to discern the information density differences between unstructured narrative passages and structured knowledge triplets. During inference, this predictor projects passages, triplets, and the model’s parametric memory into a unified probability space, enabling a soft, token-level fusion that dynamically optimizes information gain. Extensive experiments on four open-domain QA benchmarks demonstrate that AED-RAG significantly outperforms competitive baselines, underscoring the effectiveness of integrating multi-granular contexts.</abstract>
<identifier type="citekey">zhou-etal-2026-aed</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1148/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>22885</start>
<end>22899</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AED-RAG: Continuous Multi-Granular Context Fusion for Retrieval-Augmented Generation via Adaptive Ensemble Decoding
%A Zhou, Junzhe
%A Lin, Fulin
%A Cheng, Tairan
%A Chen, Shaowen
%A Wang, Hongwei
%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 zhou-etal-2026-aed
%X Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) yet suffers from a mismatch between coarse retrieval granularity and fine-grained generation needs. Specifically, coarse-grained passages inherently conflate valid context with intra-passage noise that semantic retrieval often fails to filter. Existing alignment strategies, typically relying on discrete reranking, struggle to address this granularity mismatch or effectively balance external evidence with internal knowledge. To bridge this gap, we propose **AED-RAG**, a framework that synergizes discrete retrieval with continuous **A**daptive **E**nsemble **D**ecoding. Specifically, we fine-tune a utility predictor using contrastive perplexity to discern the information density differences between unstructured narrative passages and structured knowledge triplets. During inference, this predictor projects passages, triplets, and the model’s parametric memory into a unified probability space, enabling a soft, token-level fusion that dynamically optimizes information gain. Extensive experiments on four open-domain QA benchmarks demonstrate that AED-RAG significantly outperforms competitive baselines, underscoring the effectiveness of integrating multi-granular contexts.
%U https://aclanthology.org/2026.findings-acl.1148/
%P 22885-22899
Markdown (Informal)
[AED-RAG: Continuous Multi-Granular Context Fusion for Retrieval-Augmented Generation via Adaptive Ensemble Decoding](https://aclanthology.org/2026.findings-acl.1148/) (Zhou et al., Findings 2026)
ACL