@inproceedings{guo-etal-2026-towards,
title = "Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-{LLM} Interactions",
author = "Guo, Qianyun and
Li, Yibo and
Liu, Yue and
Hooi, Bryan",
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.2378/",
pages = "51070--51105",
ISBN = "979-8-89176-462-0",
abstract = "Large Language Models (LLMs) are increasingly serving as personal assistants, where users may share individual preferences over extended interactions. However, assessing how well LLMs can follow these preferences in natural, long-term situations remains underexplored. This work proposes **RealPref**, a benchmark for evaluating natural preference-following in personalized user-LLM interactions. RealPref features 100 synthetic user profiles, 1300 personalized preferences, 4 types of preference expression (from explicit to implicit), and long-horizon interaction histories. It explored three types of test tasks (multiple-choice, true-or-false, and open-ended), with granular rubrics for LLM-as-a-judge evaluation. Results indicate that LLM performance drops significantly as context length grows and preference expression becomes more implicit, and that generalizing user preference understanding to unseen scenarios poses further challenges. RealPref and these findings provide a foundation for future research to develop user-aware LLM assistants that better adapt to individual needs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-towards">
<titleInfo>
<title>Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qianyun</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yibo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Hooi</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>Large Language Models (LLMs) are increasingly serving as personal assistants, where users may share individual preferences over extended interactions. However, assessing how well LLMs can follow these preferences in natural, long-term situations remains underexplored. This work proposes **RealPref**, a benchmark for evaluating natural preference-following in personalized user-LLM interactions. RealPref features 100 synthetic user profiles, 1300 personalized preferences, 4 types of preference expression (from explicit to implicit), and long-horizon interaction histories. It explored three types of test tasks (multiple-choice, true-or-false, and open-ended), with granular rubrics for LLM-as-a-judge evaluation. Results indicate that LLM performance drops significantly as context length grows and preference expression becomes more implicit, and that generalizing user preference understanding to unseen scenarios poses further challenges. RealPref and these findings provide a foundation for future research to develop user-aware LLM assistants that better adapt to individual needs.</abstract>
<identifier type="citekey">guo-etal-2026-towards</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2378/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>51070</start>
<end>51105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
%A Guo, Qianyun
%A Li, Yibo
%A Liu, Yue
%A Hooi, Bryan
%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 guo-etal-2026-towards
%X Large Language Models (LLMs) are increasingly serving as personal assistants, where users may share individual preferences over extended interactions. However, assessing how well LLMs can follow these preferences in natural, long-term situations remains underexplored. This work proposes **RealPref**, a benchmark for evaluating natural preference-following in personalized user-LLM interactions. RealPref features 100 synthetic user profiles, 1300 personalized preferences, 4 types of preference expression (from explicit to implicit), and long-horizon interaction histories. It explored three types of test tasks (multiple-choice, true-or-false, and open-ended), with granular rubrics for LLM-as-a-judge evaluation. Results indicate that LLM performance drops significantly as context length grows and preference expression becomes more implicit, and that generalizing user preference understanding to unseen scenarios poses further challenges. RealPref and these findings provide a foundation for future research to develop user-aware LLM assistants that better adapt to individual needs.
%U https://aclanthology.org/2026.findings-emnlp.2378/
%P 51070-51105
Markdown (Informal)
[Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions](https://aclanthology.org/2026.findings-emnlp.2378/) (Guo et al., Findings 2026)
ACL