@inproceedings{ma-etal-2025-drama,
title = "{DRAMA}: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers",
author = "Ma, Xueguang and
Lin, Xi Victoria and
Oguz, Barlas and
Lin, Jimmy and
Yih, Wen-tau and
Chen, Xilun",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1457/",
doi = "10.18653/v1/2025.acl-long.1457",
pages = "30170--30186",
ISBN = "979-8-89176-251-0",
abstract = "Large language models (LLMs) have demonstrated strong effectiveness and robustness when fine-tuned as dense retrievers.However, their large parameter size presents significant computational challenges at inference time.While smaller retrievers offer better efficiency, they often fail to generalize effectively with limited supervised fine-tuning data.In this work, we introduce DRAMA, a training framework that leverages LLMs to train smaller generalizable dense retrievers.In particular, we adopt pruned LLMs as the backbone and train on diverse LLM-augmented data in a single-stage contrastive learning setup.Experiments show that DRAMA offers better multilingual and long-context capabilities than traditional encoder-based retrievers, and achieves strong performance across multiple tasks and languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2025-drama">
<titleInfo>
<title>DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xueguang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="given">Victoria</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barlas</namePart>
<namePart type="family">Oguz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimmy</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xilun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have demonstrated strong effectiveness and robustness when fine-tuned as dense retrievers.However, their large parameter size presents significant computational challenges at inference time.While smaller retrievers offer better efficiency, they often fail to generalize effectively with limited supervised fine-tuning data.In this work, we introduce DRAMA, a training framework that leverages LLMs to train smaller generalizable dense retrievers.In particular, we adopt pruned LLMs as the backbone and train on diverse LLM-augmented data in a single-stage contrastive learning setup.Experiments show that DRAMA offers better multilingual and long-context capabilities than traditional encoder-based retrievers, and achieves strong performance across multiple tasks and languages.</abstract>
<identifier type="citekey">ma-etal-2025-drama</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1457</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1457/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>30170</start>
<end>30186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers
%A Ma, Xueguang
%A Lin, Xi Victoria
%A Oguz, Barlas
%A Lin, Jimmy
%A Yih, Wen-tau
%A Chen, Xilun
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F ma-etal-2025-drama
%X Large language models (LLMs) have demonstrated strong effectiveness and robustness when fine-tuned as dense retrievers.However, their large parameter size presents significant computational challenges at inference time.While smaller retrievers offer better efficiency, they often fail to generalize effectively with limited supervised fine-tuning data.In this work, we introduce DRAMA, a training framework that leverages LLMs to train smaller generalizable dense retrievers.In particular, we adopt pruned LLMs as the backbone and train on diverse LLM-augmented data in a single-stage contrastive learning setup.Experiments show that DRAMA offers better multilingual and long-context capabilities than traditional encoder-based retrievers, and achieves strong performance across multiple tasks and languages.
%R 10.18653/v1/2025.acl-long.1457
%U https://aclanthology.org/2025.acl-long.1457/
%U https://doi.org/10.18653/v1/2025.acl-long.1457
%P 30170-30186
Markdown (Informal)
[DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers](https://aclanthology.org/2025.acl-long.1457/) (Ma et al., ACL 2025)
ACL