@inproceedings{li-etal-2026-bridging,
title = "Bridging {SLM}s and {LLM}s: A Lightweight Framework for Knowledge Injection",
author = "Li, Zihao and
Xu, Xuekong and
Yu, Yuqing and
Zou, Lixin and
Li, Chenliang and
Lu, Wei",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1652/",
pages = "35183--35210",
ISBN = "979-8-89176-462-0",
abstract = "While large language models (LLMs) show immense potential in specialized domains, their adaptation is often hindered by limited access to domain-specific data and the high computational cost of model training. To address these challenges, we propose a lightweight knowledge injection framework. Instead of sharing raw data directly, our approach fine-tunes a small model and transfers its knowledge vectors to the target LLM for knowledge injection, thereby reducing data exposure and computational overhead. To mitigate the knowledge loss incurred during the injection process, we further introduce an iterative knowledge calibration strategy. We theoretically bound the error of the transformation matrix and prove the stability and linear convergence of the calibration process. Comprehensive experiments demonstrate that our method significantly outperforms parameter-efficient baselines and achieves performance comparable to full-parameter fine-tuning, while consuming only 28{\%} of the GPU memory and 3{\%} of the raw training data. Code is available at https://github.com/Yuhanleeee/LiSKI."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-bridging">
<titleInfo>
<title>Bridging SLMs and LLMs: A Lightweight Framework for Knowledge Injection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zihao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuekong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqing</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lixin</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenliang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>While large language models (LLMs) show immense potential in specialized domains, their adaptation is often hindered by limited access to domain-specific data and the high computational cost of model training. To address these challenges, we propose a lightweight knowledge injection framework. Instead of sharing raw data directly, our approach fine-tunes a small model and transfers its knowledge vectors to the target LLM for knowledge injection, thereby reducing data exposure and computational overhead. To mitigate the knowledge loss incurred during the injection process, we further introduce an iterative knowledge calibration strategy. We theoretically bound the error of the transformation matrix and prove the stability and linear convergence of the calibration process. Comprehensive experiments demonstrate that our method significantly outperforms parameter-efficient baselines and achieves performance comparable to full-parameter fine-tuning, while consuming only 28% of the GPU memory and 3% of the raw training data. Code is available at https://github.com/Yuhanleeee/LiSKI.</abstract>
<identifier type="citekey">li-etal-2026-bridging</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1652/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>35183</start>
<end>35210</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging SLMs and LLMs: A Lightweight Framework for Knowledge Injection
%A Li, Zihao
%A Xu, Xuekong
%A Yu, Yuqing
%A Zou, Lixin
%A Li, Chenliang
%A Lu, Wei
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F li-etal-2026-bridging
%X While large language models (LLMs) show immense potential in specialized domains, their adaptation is often hindered by limited access to domain-specific data and the high computational cost of model training. To address these challenges, we propose a lightweight knowledge injection framework. Instead of sharing raw data directly, our approach fine-tunes a small model and transfers its knowledge vectors to the target LLM for knowledge injection, thereby reducing data exposure and computational overhead. To mitigate the knowledge loss incurred during the injection process, we further introduce an iterative knowledge calibration strategy. We theoretically bound the error of the transformation matrix and prove the stability and linear convergence of the calibration process. Comprehensive experiments demonstrate that our method significantly outperforms parameter-efficient baselines and achieves performance comparable to full-parameter fine-tuning, while consuming only 28% of the GPU memory and 3% of the raw training data. Code is available at https://github.com/Yuhanleeee/LiSKI.
%U https://aclanthology.org/2026.findings-emnlp.1652/
%P 35183-35210
Markdown (Informal)
[Bridging SLMs and LLMs: A Lightweight Framework for Knowledge Injection](https://aclanthology.org/2026.findings-emnlp.1652/) (Li et al., Findings 2026)
ACL