@inproceedings{zhao-etal-2025-improving,
title = "Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework",
author = "Zhao, Qi and
Song, Qi and
Xie, Tian and
Zhang, Haiyue and
Yang, Hongyu and
Li, Xiangyang",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.213/",
doi = "10.18653/v1/2025.findings-naacl.213",
pages = "3860--3871",
ISBN = "979-8-89176-195-7",
abstract = "Pre-trained language models (PLMs) are widely used in NLP but struggle with capturing entity knowledge. To address this, knowledge enhancement techniques have been proposed. However, existing methods rely heavily on external knowledge bases embedding and often introduce noisy entity representations. In this work, we propose a novel **K**nowledge **E**nhancement **F**iltering **F**ramework named KEFF, which contains both knowledge enhancement and knowledge enhancement filtering modules for PLM. We find that there are certain redundant bits in the embedding space of PLMs. Building on this insight, we implement knowledge-enhanced mapping of redundant bit values in entity span tokens. In order to solve the knowledge enhancement problem of existing methods that introduce noisy entity representation knowledge, we further propose a novel knowledge enhancement filter based on our knowledge enhancement method. Finally, experiments on four knowledge-driven NLP tasks show that our method effectively improves the ability of PLMs on downstream tasks. Compared to state-of-the-art approachs, our method achieves the highest F1-score and accuracy, while reducing the computational cost by 1.7-2.5x."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2025-improving">
<titleInfo>
<title>Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Pre-trained language models (PLMs) are widely used in NLP but struggle with capturing entity knowledge. To address this, knowledge enhancement techniques have been proposed. However, existing methods rely heavily on external knowledge bases embedding and often introduce noisy entity representations. In this work, we propose a novel **K**nowledge **E**nhancement **F**iltering **F**ramework named KEFF, which contains both knowledge enhancement and knowledge enhancement filtering modules for PLM. We find that there are certain redundant bits in the embedding space of PLMs. Building on this insight, we implement knowledge-enhanced mapping of redundant bit values in entity span tokens. In order to solve the knowledge enhancement problem of existing methods that introduce noisy entity representation knowledge, we further propose a novel knowledge enhancement filter based on our knowledge enhancement method. Finally, experiments on four knowledge-driven NLP tasks show that our method effectively improves the ability of PLMs on downstream tasks. Compared to state-of-the-art approachs, our method achieves the highest F1-score and accuracy, while reducing the computational cost by 1.7-2.5x.</abstract>
<identifier type="citekey">zhao-etal-2025-improving</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.213</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.213/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3860</start>
<end>3871</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework
%A Zhao, Qi
%A Song, Qi
%A Xie, Tian
%A Zhang, Haiyue
%A Yang, Hongyu
%A Li, Xiangyang
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F zhao-etal-2025-improving
%X Pre-trained language models (PLMs) are widely used in NLP but struggle with capturing entity knowledge. To address this, knowledge enhancement techniques have been proposed. However, existing methods rely heavily on external knowledge bases embedding and often introduce noisy entity representations. In this work, we propose a novel **K**nowledge **E**nhancement **F**iltering **F**ramework named KEFF, which contains both knowledge enhancement and knowledge enhancement filtering modules for PLM. We find that there are certain redundant bits in the embedding space of PLMs. Building on this insight, we implement knowledge-enhanced mapping of redundant bit values in entity span tokens. In order to solve the knowledge enhancement problem of existing methods that introduce noisy entity representation knowledge, we further propose a novel knowledge enhancement filter based on our knowledge enhancement method. Finally, experiments on four knowledge-driven NLP tasks show that our method effectively improves the ability of PLMs on downstream tasks. Compared to state-of-the-art approachs, our method achieves the highest F1-score and accuracy, while reducing the computational cost by 1.7-2.5x.
%R 10.18653/v1/2025.findings-naacl.213
%U https://aclanthology.org/2025.findings-naacl.213/
%U https://doi.org/10.18653/v1/2025.findings-naacl.213
%P 3860-3871
Markdown (Informal)
[Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework](https://aclanthology.org/2025.findings-naacl.213/) (Zhao et al., Findings 2025)
ACL