@inproceedings{nayeem-rafiei-2024-kidlm,
title = "{K}id{LM}: Advancing Language Models for Children {--} Early Insights and Future Directions",
author = "Nayeem, Mir Tafseer and
Rafiei, Davood",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.277",
doi = "10.18653/v1/2024.emnlp-main.277",
pages = "4813--4836",
abstract = "Recent studies highlight the potential of large language models in creating educational tools for children, yet significant challenges remain in maintaining key child-specific properties such as linguistic nuances, cognitive needs, and safety standards. In this paper, we explore foundational steps toward the development of child-specific language models, emphasizing the necessity of high-quality pre-training data. We introduce a novel user-centric data collection pipeline that involves gathering and validating a corpus specifically written for and sometimes by children. Additionally, we propose a new training objective, Stratified Masking, which dynamically adjusts masking probabilities based on our domain-specific child language data, enabling models to prioritize vocabulary and concepts more suitable for children. Experimental evaluations demonstrate that our model excels in understanding lower grade-level text, maintains safety by avoiding stereotypes, and captures children{'}s unique preferences. Furthermore, we provide actionable insights for future research and development in child-specific language modeling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nayeem-rafiei-2024-kidlm">
<titleInfo>
<title>KidLM: Advancing Language Models for Children – Early Insights and Future Directions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mir</namePart>
<namePart type="given">Tafseer</namePart>
<namePart type="family">Nayeem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davood</namePart>
<namePart type="family">Rafiei</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>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</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>Recent studies highlight the potential of large language models in creating educational tools for children, yet significant challenges remain in maintaining key child-specific properties such as linguistic nuances, cognitive needs, and safety standards. In this paper, we explore foundational steps toward the development of child-specific language models, emphasizing the necessity of high-quality pre-training data. We introduce a novel user-centric data collection pipeline that involves gathering and validating a corpus specifically written for and sometimes by children. Additionally, we propose a new training objective, Stratified Masking, which dynamically adjusts masking probabilities based on our domain-specific child language data, enabling models to prioritize vocabulary and concepts more suitable for children. Experimental evaluations demonstrate that our model excels in understanding lower grade-level text, maintains safety by avoiding stereotypes, and captures children’s unique preferences. Furthermore, we provide actionable insights for future research and development in child-specific language modeling.</abstract>
<identifier type="citekey">nayeem-rafiei-2024-kidlm</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.277</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.277</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>4813</start>
<end>4836</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KidLM: Advancing Language Models for Children – Early Insights and Future Directions
%A Nayeem, Mir Tafseer
%A Rafiei, Davood
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F nayeem-rafiei-2024-kidlm
%X Recent studies highlight the potential of large language models in creating educational tools for children, yet significant challenges remain in maintaining key child-specific properties such as linguistic nuances, cognitive needs, and safety standards. In this paper, we explore foundational steps toward the development of child-specific language models, emphasizing the necessity of high-quality pre-training data. We introduce a novel user-centric data collection pipeline that involves gathering and validating a corpus specifically written for and sometimes by children. Additionally, we propose a new training objective, Stratified Masking, which dynamically adjusts masking probabilities based on our domain-specific child language data, enabling models to prioritize vocabulary and concepts more suitable for children. Experimental evaluations demonstrate that our model excels in understanding lower grade-level text, maintains safety by avoiding stereotypes, and captures children’s unique preferences. Furthermore, we provide actionable insights for future research and development in child-specific language modeling.
%R 10.18653/v1/2024.emnlp-main.277
%U https://aclanthology.org/2024.emnlp-main.277
%U https://doi.org/10.18653/v1/2024.emnlp-main.277
%P 4813-4836
Markdown (Informal)
[KidLM: Advancing Language Models for Children – Early Insights and Future Directions](https://aclanthology.org/2024.emnlp-main.277) (Nayeem & Rafiei, EMNLP 2024)
ACL