@inproceedings{mok-etal-2025-exploring,
title = "Exploring the Potential of {LLM}s as Personalized Assistants: Dataset, Evaluation, and Analysis",
author = "Mok, Jisoo and
Kim, Ik-hwan and
Park, Sangkwon and
Yoon, Sungroh",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.504/",
doi = "10.18653/v1/2025.acl-long.504",
pages = "10212--10239",
ISBN = "979-8-89176-251-0",
abstract = "Personalized AI assistants, a hallmark of the human-like capabilities of Large Language Models (LLMs), are a challenging application that intertwines multiple problems in LLM research. Despite the growing interest in the development of personalized assistants, the lack of an open-source conversational dataset tailored for personalization remains a significant obstacle for researchers in the field. To address this research gap, we introduce HiCUPID, a new benchmark to probe and unleash the potential of LLMs to deliver personalized responses. Alongside a conversational dataset, HiCUPID provides a Llama-3.2-based automated evaluation model whose assessment closely mirrors human preferences. We release our dataset, evaluation model, and code at https://github.com/12kimih/HiCUPID."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mok-etal-2025-exploring">
<titleInfo>
<title>Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jisoo</namePart>
<namePart type="family">Mok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ik-hwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sangkwon</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungroh</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Personalized AI assistants, a hallmark of the human-like capabilities of Large Language Models (LLMs), are a challenging application that intertwines multiple problems in LLM research. Despite the growing interest in the development of personalized assistants, the lack of an open-source conversational dataset tailored for personalization remains a significant obstacle for researchers in the field. To address this research gap, we introduce HiCUPID, a new benchmark to probe and unleash the potential of LLMs to deliver personalized responses. Alongside a conversational dataset, HiCUPID provides a Llama-3.2-based automated evaluation model whose assessment closely mirrors human preferences. We release our dataset, evaluation model, and code at https://github.com/12kimih/HiCUPID.</abstract>
<identifier type="citekey">mok-etal-2025-exploring</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.504</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.504/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>10212</start>
<end>10239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis
%A Mok, Jisoo
%A Kim, Ik-hwan
%A Park, Sangkwon
%A Yoon, Sungroh
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F mok-etal-2025-exploring
%X Personalized AI assistants, a hallmark of the human-like capabilities of Large Language Models (LLMs), are a challenging application that intertwines multiple problems in LLM research. Despite the growing interest in the development of personalized assistants, the lack of an open-source conversational dataset tailored for personalization remains a significant obstacle for researchers in the field. To address this research gap, we introduce HiCUPID, a new benchmark to probe and unleash the potential of LLMs to deliver personalized responses. Alongside a conversational dataset, HiCUPID provides a Llama-3.2-based automated evaluation model whose assessment closely mirrors human preferences. We release our dataset, evaluation model, and code at https://github.com/12kimih/HiCUPID.
%R 10.18653/v1/2025.acl-long.504
%U https://aclanthology.org/2025.acl-long.504/
%U https://doi.org/10.18653/v1/2025.acl-long.504
%P 10212-10239
Markdown (Informal)
[Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis](https://aclanthology.org/2025.acl-long.504/) (Mok et al., ACL 2025)
ACL