@inproceedings{lee-etal-2025-trag,
title = "t{RAG}: Term-level Retrieval-Augmented Generation for Domain-Adaptive Retrieval",
author = "Lee, Dohyeon and
Kim, Jongyoon and
Kim, Jihyuk and
Hwang, Seung-won and
Park, Joonsuk",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.334/",
pages = "6566--6578",
ISBN = "979-8-89176-189-6",
abstract = "Neural retrieval models have emerged as an effective tool for information retrieval, but their performance suffers when there is a domain shift between training and test data distributions. Recent work aims to construct pseudo-training data for the target domain by generating domain-adapted pseudo-queries using large language models (LLMs). However, we identifies that LLMs exhibit a {\textquotedblleft}seen term bias{\textquotedblright} where the generated pseudo-queries fail to include relevant {\textquotedblleft}unseen{\textquotedblright} terms as expected for domain adaptation purposes. To address this limitation, we propose to improve the term recall of unseen query terms, by using term-level Retrieval-Augmented Generation (tRAG). Specifically, unlike existing document-level RAG, we propose to generate domain-specific keywords from all documents in the corpus, including those unseen in any individual document. To filter hallucination, generated keywords are retrieved and reranked, leveraging relevance feedback from both retrievers and LLMs. Experiments on the BEIR benchmark show tRAG significantly improves recall for unseen terms by 10.6{\%} and outperforms LLM and retrieval-augmented generation baselines on overall retrieval performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2025-trag">
<titleInfo>
<title>tRAG: Term-level Retrieval-Augmented Generation for Domain-Adaptive Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dohyeon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Jihyuk</namePart>
<namePart type="family">Kim</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>
<name type="personal">
<namePart type="given">Joonsuk</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Neural retrieval models have emerged as an effective tool for information retrieval, but their performance suffers when there is a domain shift between training and test data distributions. Recent work aims to construct pseudo-training data for the target domain by generating domain-adapted pseudo-queries using large language models (LLMs). However, we identifies that LLMs exhibit a “seen term bias” where the generated pseudo-queries fail to include relevant “unseen” terms as expected for domain adaptation purposes. To address this limitation, we propose to improve the term recall of unseen query terms, by using term-level Retrieval-Augmented Generation (tRAG). Specifically, unlike existing document-level RAG, we propose to generate domain-specific keywords from all documents in the corpus, including those unseen in any individual document. To filter hallucination, generated keywords are retrieved and reranked, leveraging relevance feedback from both retrievers and LLMs. Experiments on the BEIR benchmark show tRAG significantly improves recall for unseen terms by 10.6% and outperforms LLM and retrieval-augmented generation baselines on overall retrieval performance.</abstract>
<identifier type="citekey">lee-etal-2025-trag</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.334/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6566</start>
<end>6578</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T tRAG: Term-level Retrieval-Augmented Generation for Domain-Adaptive Retrieval
%A Lee, Dohyeon
%A Kim, Jongyoon
%A Kim, Jihyuk
%A Hwang, Seung-won
%A Park, Joonsuk
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F lee-etal-2025-trag
%X Neural retrieval models have emerged as an effective tool for information retrieval, but their performance suffers when there is a domain shift between training and test data distributions. Recent work aims to construct pseudo-training data for the target domain by generating domain-adapted pseudo-queries using large language models (LLMs). However, we identifies that LLMs exhibit a “seen term bias” where the generated pseudo-queries fail to include relevant “unseen” terms as expected for domain adaptation purposes. To address this limitation, we propose to improve the term recall of unseen query terms, by using term-level Retrieval-Augmented Generation (tRAG). Specifically, unlike existing document-level RAG, we propose to generate domain-specific keywords from all documents in the corpus, including those unseen in any individual document. To filter hallucination, generated keywords are retrieved and reranked, leveraging relevance feedback from both retrievers and LLMs. Experiments on the BEIR benchmark show tRAG significantly improves recall for unseen terms by 10.6% and outperforms LLM and retrieval-augmented generation baselines on overall retrieval performance.
%U https://aclanthology.org/2025.naacl-long.334/
%P 6566-6578
Markdown (Informal)
[tRAG: Term-level Retrieval-Augmented Generation for Domain-Adaptive Retrieval](https://aclanthology.org/2025.naacl-long.334/) (Lee et al., NAACL 2025)
ACL
- Dohyeon Lee, Jongyoon Kim, Jihyuk Kim, Seung-won Hwang, and Joonsuk Park. 2025. tRAG: Term-level Retrieval-Augmented Generation for Domain-Adaptive Retrieval. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6566–6578, Albuquerque, New Mexico. Association for Computational Linguistics.