@inproceedings{he-etal-2025-refining,
title = "Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models",
author = "He, Liyang and
Liu, Chenglong and
Li, Rui and
Huang, Zhenya and
Ruan, Shulan and
Zhou, Jun and
Chen, Enhong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.553/",
doi = "10.18653/v1/2025.findings-acl.553",
pages = "10627--10643",
ISBN = "979-8-89176-256-5",
abstract = "Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using annotated datasets like NLI. Yet, the reliance on manual labels limits scalability. Recent studies leverage large language models (LLMs) to generate sentence pairs, reducing annotation dependency. However, they overlook ranking information crucial for fine-grained semantic distinctions. To tackle this challenge, we propose a method for controlling the generation direction of LLMs in the latent space. Unlike unconstrained generation, the controlled approach ensures meaningful semantic divergence. Then, we refine exist sentence embedding model by integrating ranking information and semantic information. Experiments on multiple benchmarks demonstrate that our method achieves new SOTA performance with a modest cost in ranking sentence synthesis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2025-refining">
<titleInfo>
<title>Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liyang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenglong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenya</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shulan</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enhong</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using annotated datasets like NLI. Yet, the reliance on manual labels limits scalability. Recent studies leverage large language models (LLMs) to generate sentence pairs, reducing annotation dependency. However, they overlook ranking information crucial for fine-grained semantic distinctions. To tackle this challenge, we propose a method for controlling the generation direction of LLMs in the latent space. Unlike unconstrained generation, the controlled approach ensures meaningful semantic divergence. Then, we refine exist sentence embedding model by integrating ranking information and semantic information. Experiments on multiple benchmarks demonstrate that our method achieves new SOTA performance with a modest cost in ranking sentence synthesis.</abstract>
<identifier type="citekey">he-etal-2025-refining</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.553</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.553/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>10627</start>
<end>10643</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models
%A He, Liyang
%A Liu, Chenglong
%A Li, Rui
%A Huang, Zhenya
%A Ruan, Shulan
%A Zhou, Jun
%A Chen, Enhong
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F he-etal-2025-refining
%X Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using annotated datasets like NLI. Yet, the reliance on manual labels limits scalability. Recent studies leverage large language models (LLMs) to generate sentence pairs, reducing annotation dependency. However, they overlook ranking information crucial for fine-grained semantic distinctions. To tackle this challenge, we propose a method for controlling the generation direction of LLMs in the latent space. Unlike unconstrained generation, the controlled approach ensures meaningful semantic divergence. Then, we refine exist sentence embedding model by integrating ranking information and semantic information. Experiments on multiple benchmarks demonstrate that our method achieves new SOTA performance with a modest cost in ranking sentence synthesis.
%R 10.18653/v1/2025.findings-acl.553
%U https://aclanthology.org/2025.findings-acl.553/
%U https://doi.org/10.18653/v1/2025.findings-acl.553
%P 10627-10643
Markdown (Informal)
[Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models](https://aclanthology.org/2025.findings-acl.553/) (He et al., Findings 2025)
ACL