@inproceedings{kim-etal-2026-unite,
title = "{U}n{I}te: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval",
author = "Kim, Jongyoon and
Hwang, Minseong and
Hwang, Seung-won",
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.1614/",
doi = "10.18653/v1/2026.findings-acl.1614",
pages = "32256--32272",
ISBN = "979-8-89176-395-1",
abstract = "Unsupervised domain adaptation generalizes neural retrievers to an unseen domain by generating pseudo queries on target domain documents. The quality and efficiency of this adaptation critically depend on which documents are selected for pseudo query generation. The existing document sampling method focuses on diversity but fails to capture model uncertainty. In contrast, we propose Uncertainty-based Iterative Document Sampling (UnIte), addressing these limitations by (1) filtering documents with high aleatoric uncertainty and (2) prioritizing those with high epistemic uncertainty, maximizing the learning utility of the current model. We conducted extensive experiments on a large corpus of BEIR with small and large models, showing significant gains of +2.45 and +3.49 nDCG@10 with a smaller training sample size, 4k on average."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-unite">
<titleInfo>
<title>UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jongyoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minseong</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-won</namePart>
<namePart type="family">Hwang</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>Unsupervised domain adaptation generalizes neural retrievers to an unseen domain by generating pseudo queries on target domain documents. The quality and efficiency of this adaptation critically depend on which documents are selected for pseudo query generation. The existing document sampling method focuses on diversity but fails to capture model uncertainty. In contrast, we propose Uncertainty-based Iterative Document Sampling (UnIte), addressing these limitations by (1) filtering documents with high aleatoric uncertainty and (2) prioritizing those with high epistemic uncertainty, maximizing the learning utility of the current model. We conducted extensive experiments on a large corpus of BEIR with small and large models, showing significant gains of +2.45 and +3.49 nDCG@10 with a smaller training sample size, 4k on average.</abstract>
<identifier type="citekey">kim-etal-2026-unite</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1614</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1614/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>32256</start>
<end>32272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval
%A Kim, Jongyoon
%A Hwang, Minseong
%A Hwang, Seung-won
%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 kim-etal-2026-unite
%X Unsupervised domain adaptation generalizes neural retrievers to an unseen domain by generating pseudo queries on target domain documents. The quality and efficiency of this adaptation critically depend on which documents are selected for pseudo query generation. The existing document sampling method focuses on diversity but fails to capture model uncertainty. In contrast, we propose Uncertainty-based Iterative Document Sampling (UnIte), addressing these limitations by (1) filtering documents with high aleatoric uncertainty and (2) prioritizing those with high epistemic uncertainty, maximizing the learning utility of the current model. We conducted extensive experiments on a large corpus of BEIR with small and large models, showing significant gains of +2.45 and +3.49 nDCG@10 with a smaller training sample size, 4k on average.
%R 10.18653/v1/2026.findings-acl.1614
%U https://aclanthology.org/2026.findings-acl.1614/
%U https://doi.org/10.18653/v1/2026.findings-acl.1614
%P 32256-32272
Markdown (Informal)
[UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval](https://aclanthology.org/2026.findings-acl.1614/) (Kim et al., Findings 2026)
ACL