@inproceedings{candello-etal-2025-collaborative,
title = "Collaborative Co-Design Practices for Supporting Synthetic Data Generation in Large Language Models: A Pilot Study",
author = "Candello, Heloisa and
Horesh, Raya and
Adebiyi, Aminat and
Azmat, Muneeza and
de Paula, Rog{\'e}rio Abreu and
Chiazor, Lamogha",
editor = "Blodgett, Su Lin and
Curry, Amanda Cercas and
Dev, Sunipa and
Li, Siyan and
Madaio, Michael and
Wang, Jack and
Wu, Sherry Tongshuang and
Xiao, Ziang and
Yang, Diyi",
booktitle = "Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.hcinlp-1.11/",
pages = "129--147",
ISBN = "979-8-89176-353-1",
abstract = "Large language models (LLMs) are increasingly embedded in development pipelines and the daily workflows of AI practitioners. However, their effectiveness depends on access to high-quality datasets that are sufficiently large, diverse, and contextually relevant. Existing datasets often fall short of these requirements, prompting the use of synthetic data (SD) generation. A critical step in this process is the creation of human seed examples, which guide the generation of SD tailored to specific tasks. We propose a participatory methodology for seed example generation, involving multidisciplinary teams in structured workshops to co-create examples aligned with Responsible AI principles. In a pilot study with a Responsible AI team, we facilitated hands-on activities to produce seed examples and evaluated the resulting data across three dimensions: diversity, sensibility, and relevance. Our findings suggest that participatory approaches can enhance the representativeness and contextual fidelity of synthetic datasets. We provide a reproducible framework to support NLP practitioners in generating high-quality seed data for LLM development and deployment"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="candello-etal-2025-collaborative">
<titleInfo>
<title>Collaborative Co-Design Practices for Supporting Synthetic Data Generation in Large Language Models: A Pilot Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heloisa</namePart>
<namePart type="family">Candello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raya</namePart>
<namePart type="family">Horesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aminat</namePart>
<namePart type="family">Adebiyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muneeza</namePart>
<namePart type="family">Azmat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rogério</namePart>
<namePart type="given">Abreu</namePart>
<namePart type="family">de Paula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamogha</namePart>
<namePart type="family">Chiazor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Su</namePart>
<namePart type="given">Lin</namePart>
<namePart type="family">Blodgett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="given">Cercas</namePart>
<namePart type="family">Curry</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">Siyan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Madaio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sherry</namePart>
<namePart type="given">Tongshuang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziang</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-353-1</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly embedded in development pipelines and the daily workflows of AI practitioners. However, their effectiveness depends on access to high-quality datasets that are sufficiently large, diverse, and contextually relevant. Existing datasets often fall short of these requirements, prompting the use of synthetic data (SD) generation. A critical step in this process is the creation of human seed examples, which guide the generation of SD tailored to specific tasks. We propose a participatory methodology for seed example generation, involving multidisciplinary teams in structured workshops to co-create examples aligned with Responsible AI principles. In a pilot study with a Responsible AI team, we facilitated hands-on activities to produce seed examples and evaluated the resulting data across three dimensions: diversity, sensibility, and relevance. Our findings suggest that participatory approaches can enhance the representativeness and contextual fidelity of synthetic datasets. We provide a reproducible framework to support NLP practitioners in generating high-quality seed data for LLM development and deployment</abstract>
<identifier type="citekey">candello-etal-2025-collaborative</identifier>
<location>
<url>https://aclanthology.org/2025.hcinlp-1.11/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>129</start>
<end>147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collaborative Co-Design Practices for Supporting Synthetic Data Generation in Large Language Models: A Pilot Study
%A Candello, Heloisa
%A Horesh, Raya
%A Adebiyi, Aminat
%A Azmat, Muneeza
%A de Paula, Rogério Abreu
%A Chiazor, Lamogha
%Y Blodgett, Su Lin
%Y Curry, Amanda Cercas
%Y Dev, Sunipa
%Y Li, Siyan
%Y Madaio, Michael
%Y Wang, Jack
%Y Wu, Sherry Tongshuang
%Y Xiao, Ziang
%Y Yang, Diyi
%S Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-353-1
%F candello-etal-2025-collaborative
%X Large language models (LLMs) are increasingly embedded in development pipelines and the daily workflows of AI practitioners. However, their effectiveness depends on access to high-quality datasets that are sufficiently large, diverse, and contextually relevant. Existing datasets often fall short of these requirements, prompting the use of synthetic data (SD) generation. A critical step in this process is the creation of human seed examples, which guide the generation of SD tailored to specific tasks. We propose a participatory methodology for seed example generation, involving multidisciplinary teams in structured workshops to co-create examples aligned with Responsible AI principles. In a pilot study with a Responsible AI team, we facilitated hands-on activities to produce seed examples and evaluated the resulting data across three dimensions: diversity, sensibility, and relevance. Our findings suggest that participatory approaches can enhance the representativeness and contextual fidelity of synthetic datasets. We provide a reproducible framework to support NLP practitioners in generating high-quality seed data for LLM development and deployment
%U https://aclanthology.org/2025.hcinlp-1.11/
%P 129-147
Markdown (Informal)
[Collaborative Co-Design Practices for Supporting Synthetic Data Generation in Large Language Models: A Pilot Study](https://aclanthology.org/2025.hcinlp-1.11/) (Candello et al., HCINLP 2025)
ACL