@inproceedings{jiang-etal-2024-scaling,
title = "Scaling Sentence Embeddings with Large Language Models",
author = "Jiang, Ting and
Huang, Shaohan and
Luan, Zhongzhi and
Wang, Deqing and
Zhuang, Fuzhen",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.181",
pages = "3182--3196",
abstract = "Large Language Models (LLMs) have recently gained significant interest due to their impressive results in various natural language tasks. However, their application to sentence embeddings is still under active research. In this work, we introduce PromptEOL, a simple and efficient method designed to enhance LLM performance on sentence embeddings with a one-word limitation. We further integrate PromptEOL with in-context learning and alignment to leverage LLMs in two settings: without fine-tuning and with fine-tuning. Our extensive experiments show that PromptEOL enables LLMs to generate superior sentence embeddings without fine-tuning, outperforming contrastive learning methods. Additionally, with fine-tuning, a 2.7B parameter model using PromptEOL surpasses the performance of a 4.8B parameter model from previous methods. We also analyze how scaling model parameters, from 125 million to 66 billion, impacts sentence embedding performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2024-scaling">
<titleInfo>
<title>Scaling Sentence Embeddings with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaohan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongzhi</namePart>
<namePart type="family">Luan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuzhen</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have recently gained significant interest due to their impressive results in various natural language tasks. However, their application to sentence embeddings is still under active research. In this work, we introduce PromptEOL, a simple and efficient method designed to enhance LLM performance on sentence embeddings with a one-word limitation. We further integrate PromptEOL with in-context learning and alignment to leverage LLMs in two settings: without fine-tuning and with fine-tuning. Our extensive experiments show that PromptEOL enables LLMs to generate superior sentence embeddings without fine-tuning, outperforming contrastive learning methods. Additionally, with fine-tuning, a 2.7B parameter model using PromptEOL surpasses the performance of a 4.8B parameter model from previous methods. We also analyze how scaling model parameters, from 125 million to 66 billion, impacts sentence embedding performance.</abstract>
<identifier type="citekey">jiang-etal-2024-scaling</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.181</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>3182</start>
<end>3196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scaling Sentence Embeddings with Large Language Models
%A Jiang, Ting
%A Huang, Shaohan
%A Luan, Zhongzhi
%A Wang, Deqing
%A Zhuang, Fuzhen
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F jiang-etal-2024-scaling
%X Large Language Models (LLMs) have recently gained significant interest due to their impressive results in various natural language tasks. However, their application to sentence embeddings is still under active research. In this work, we introduce PromptEOL, a simple and efficient method designed to enhance LLM performance on sentence embeddings with a one-word limitation. We further integrate PromptEOL with in-context learning and alignment to leverage LLMs in two settings: without fine-tuning and with fine-tuning. Our extensive experiments show that PromptEOL enables LLMs to generate superior sentence embeddings without fine-tuning, outperforming contrastive learning methods. Additionally, with fine-tuning, a 2.7B parameter model using PromptEOL surpasses the performance of a 4.8B parameter model from previous methods. We also analyze how scaling model parameters, from 125 million to 66 billion, impacts sentence embedding performance.
%U https://aclanthology.org/2024.findings-emnlp.181
%P 3182-3196
Markdown (Informal)
[Scaling Sentence Embeddings with Large Language Models](https://aclanthology.org/2024.findings-emnlp.181) (Jiang et al., Findings 2024)
ACL
- Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, and Fuzhen Zhuang. 2024. Scaling Sentence Embeddings with Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3182–3196, Miami, Florida, USA. Association for Computational Linguistics.