@inproceedings{rezaei-dieng-2026-vendi,
title = "Vendi-{RAG}: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With {LLM}s",
author = "Rezaei, Mohammad Reza and
Dieng, Adji Bousso",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1499/",
pages = "31909--31932",
ISBN = "979-8-89176-462-0",
abstract = "Retrieval-augmented generation (RAG) for multi-hop question answering is limited by retrieving semantically redundant documents, when reasoning instead needs diverse, complementary sources. We introduce Vendi-RAG, which treats set-level semantic diversity as a first-class retrieval objective. It combines an eigenvalue-based diversity score (the Vendi Score) with query relevance into a single Vendi Retrieval Score, embedded in an iterative loop that uses an LLM-based answer-quality signal to adaptively rebalance diversity and relevance. On HotpotQA, MuSiQue, and 2WikiMultiHopQA, Vendi-RAG improves accuracy by $+2.4$, $+1.6$, and $+2.4$ points over the strongest diversity-aware iterative baseline (Adaptive Retrieval + MMR). A fixed-$s$ variant captures most of the gain at no extra inference cost, while the LLM-judge loop adds a smaller but significant gain on hard queries. Results hold across five instruction-tuned backbones and two dense retrievers, identifying set-level retrieval diversity as a primary, controllable axis for improving multi-hop RAG."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rezaei-dieng-2026-vendi">
<titleInfo>
<title>Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Reza</namePart>
<namePart type="family">Rezaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adji</namePart>
<namePart type="given">Bousso</namePart>
<namePart type="family">Dieng</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Retrieval-augmented generation (RAG) for multi-hop question answering is limited by retrieving semantically redundant documents, when reasoning instead needs diverse, complementary sources. We introduce Vendi-RAG, which treats set-level semantic diversity as a first-class retrieval objective. It combines an eigenvalue-based diversity score (the Vendi Score) with query relevance into a single Vendi Retrieval Score, embedded in an iterative loop that uses an LLM-based answer-quality signal to adaptively rebalance diversity and relevance. On HotpotQA, MuSiQue, and 2WikiMultiHopQA, Vendi-RAG improves accuracy by +2.4, +1.6, and +2.4 points over the strongest diversity-aware iterative baseline (Adaptive Retrieval + MMR). A fixed-s variant captures most of the gain at no extra inference cost, while the LLM-judge loop adds a smaller but significant gain on hard queries. Results hold across five instruction-tuned backbones and two dense retrievers, identifying set-level retrieval diversity as a primary, controllable axis for improving multi-hop RAG.</abstract>
<identifier type="citekey">rezaei-dieng-2026-vendi</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1499/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>31909</start>
<end>31932</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs
%A Rezaei, Mohammad Reza
%A Dieng, Adji Bousso
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F rezaei-dieng-2026-vendi
%X Retrieval-augmented generation (RAG) for multi-hop question answering is limited by retrieving semantically redundant documents, when reasoning instead needs diverse, complementary sources. We introduce Vendi-RAG, which treats set-level semantic diversity as a first-class retrieval objective. It combines an eigenvalue-based diversity score (the Vendi Score) with query relevance into a single Vendi Retrieval Score, embedded in an iterative loop that uses an LLM-based answer-quality signal to adaptively rebalance diversity and relevance. On HotpotQA, MuSiQue, and 2WikiMultiHopQA, Vendi-RAG improves accuracy by +2.4, +1.6, and +2.4 points over the strongest diversity-aware iterative baseline (Adaptive Retrieval + MMR). A fixed-s variant captures most of the gain at no extra inference cost, while the LLM-judge loop adds a smaller but significant gain on hard queries. Results hold across five instruction-tuned backbones and two dense retrievers, identifying set-level retrieval diversity as a primary, controllable axis for improving multi-hop RAG.
%U https://aclanthology.org/2026.findings-emnlp.1499/
%P 31909-31932
Markdown (Informal)
[Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs](https://aclanthology.org/2026.findings-emnlp.1499/) (Rezaei & Dieng, Findings 2026)
ACL