@inproceedings{gao-etal-2026-llm-slm,
title = "{LLM}-{SLM} Collaborative Framework of Idiomatic Expression Generation",
author = "Gao, Hui and
Song, Changhao and
Zhang, Peng and
Zhang, Jing and
Yang, Chang and
Ge, Liuxian",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.555/",
pages = "12125--12145",
ISBN = "979-8-89176-390-6",
abstract = "Idiomatic Expression Generation, which aims to produce idiomatic text from plain text, is a valuable yet challenging NLP task. However, existing methods suffer from the scarcity of parallel data and dependence on high-quality manual annotations. To address this, we propose an iterative LLM-SLM (Large Language Model-Small Language Model) collaborative framework {---} Auto-IDEA, that replaces human supervision for idiomatic expression data generation. In this self-improving cycle, the LLM constructs parallel corpora (idiomatic and plain text) via bidirectional semantic reconstruction, automatically generating ``Locate-Then-Polish'' (LTP) annotations; the SLM filters low-quality corpora while continuously enhancing its verification ability through incremental learning. We instantiate Auto-IDEA for Chinese Idiom Polishing (CIP), constructing CIP-200K, a large-scale dataset of 206K parallel sentences with LTP annotations. The Qwen3-8B fine-tuned on CIP-200K achieves a 25.2{\%} absolute Idiom Polishing Accuracy (IPA) improvement over a supervised fine-tuning (SFT) baseline, outperforming DeepSeek-R1 by 6.2{\%}. Extensive experiments (e.g., Chinese idiom cloze tests and English idiom generation tasks) and human evaluations verify the generalization and effectiveness of Auto-IDEA, demonstrating a new pathway for high-quality, annotation-free data generation through LLM-SLM collaboration."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2026-llm-slm">
<titleInfo>
<title>LLM-SLM Collaborative Framework of Idiomatic Expression Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changhao</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liuxian</namePart>
<namePart type="family">Ge</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Idiomatic Expression Generation, which aims to produce idiomatic text from plain text, is a valuable yet challenging NLP task. However, existing methods suffer from the scarcity of parallel data and dependence on high-quality manual annotations. To address this, we propose an iterative LLM-SLM (Large Language Model-Small Language Model) collaborative framework — Auto-IDEA, that replaces human supervision for idiomatic expression data generation. In this self-improving cycle, the LLM constructs parallel corpora (idiomatic and plain text) via bidirectional semantic reconstruction, automatically generating “Locate-Then-Polish” (LTP) annotations; the SLM filters low-quality corpora while continuously enhancing its verification ability through incremental learning. We instantiate Auto-IDEA for Chinese Idiom Polishing (CIP), constructing CIP-200K, a large-scale dataset of 206K parallel sentences with LTP annotations. The Qwen3-8B fine-tuned on CIP-200K achieves a 25.2% absolute Idiom Polishing Accuracy (IPA) improvement over a supervised fine-tuning (SFT) baseline, outperforming DeepSeek-R1 by 6.2%. Extensive experiments (e.g., Chinese idiom cloze tests and English idiom generation tasks) and human evaluations verify the generalization and effectiveness of Auto-IDEA, demonstrating a new pathway for high-quality, annotation-free data generation through LLM-SLM collaboration.</abstract>
<identifier type="citekey">gao-etal-2026-llm-slm</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.555/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>12125</start>
<end>12145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-SLM Collaborative Framework of Idiomatic Expression Generation
%A Gao, Hui
%A Song, Changhao
%A Zhang, Peng
%A Zhang, Jing
%A Yang, Chang
%A Ge, Liuxian
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F gao-etal-2026-llm-slm
%X Idiomatic Expression Generation, which aims to produce idiomatic text from plain text, is a valuable yet challenging NLP task. However, existing methods suffer from the scarcity of parallel data and dependence on high-quality manual annotations. To address this, we propose an iterative LLM-SLM (Large Language Model-Small Language Model) collaborative framework — Auto-IDEA, that replaces human supervision for idiomatic expression data generation. In this self-improving cycle, the LLM constructs parallel corpora (idiomatic and plain text) via bidirectional semantic reconstruction, automatically generating “Locate-Then-Polish” (LTP) annotations; the SLM filters low-quality corpora while continuously enhancing its verification ability through incremental learning. We instantiate Auto-IDEA for Chinese Idiom Polishing (CIP), constructing CIP-200K, a large-scale dataset of 206K parallel sentences with LTP annotations. The Qwen3-8B fine-tuned on CIP-200K achieves a 25.2% absolute Idiom Polishing Accuracy (IPA) improvement over a supervised fine-tuning (SFT) baseline, outperforming DeepSeek-R1 by 6.2%. Extensive experiments (e.g., Chinese idiom cloze tests and English idiom generation tasks) and human evaluations verify the generalization and effectiveness of Auto-IDEA, demonstrating a new pathway for high-quality, annotation-free data generation through LLM-SLM collaboration.
%U https://aclanthology.org/2026.acl-long.555/
%P 12125-12145
Markdown (Informal)
[LLM-SLM Collaborative Framework of Idiomatic Expression Generation](https://aclanthology.org/2026.acl-long.555/) (Gao et al., ACL 2026)
ACL
- Hui Gao, Changhao Song, Peng Zhang, Jing Zhang, Chang Yang, and Liuxian Ge. 2026. LLM-SLM Collaborative Framework of Idiomatic Expression Generation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12125–12145, San Diego, California, United States. Association for Computational Linguistics.