@inproceedings{wang-etal-2026-curp,
title = "{CURP}: Codebook-based Continuous User Representation for Personalized Generation with {LLM}s",
author = "Wang, Liang and
Mou, Xinyi and
Liu, Xiaoyou and
Huang, Xuanjing and
Wei, Zhongyu",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.340/",
pages = "7839--7860",
ISBN = "979-8-89176-459-0",
abstract = "User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation with Large Language Models (LLMs) in contemporary approaches. However, existing methods, whether personalized prompt-based or parameter-based methods, face challenges in balancing personalization quality against computational and data efficiency. We propose a novel framework CURP, which employs a bidirectional user encoder, a discrete prototype codebook and a dual-aggregator to extract both multi-dimensional user traits and query-aware user characteristic. This design enables plug-and-play personalization with a small number of trainable parameters (about 28M parameters, about 0.36{\%} of the total model size). Through extensive experiments, we show that CURP achieves superior performance and generalization compared to strong baselines on the language model personalization (LaMP) benchmark, while offering better interpretability and robustness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-curp">
<titleInfo>
<title>CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Mou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyou</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation with Large Language Models (LLMs) in contemporary approaches. However, existing methods, whether personalized prompt-based or parameter-based methods, face challenges in balancing personalization quality against computational and data efficiency. We propose a novel framework CURP, which employs a bidirectional user encoder, a discrete prototype codebook and a dual-aggregator to extract both multi-dimensional user traits and query-aware user characteristic. This design enables plug-and-play personalization with a small number of trainable parameters (about 28M parameters, about 0.36% of the total model size). Through extensive experiments, we show that CURP achieves superior performance and generalization compared to strong baselines on the language model personalization (LaMP) benchmark, while offering better interpretability and robustness.</abstract>
<identifier type="citekey">wang-etal-2026-curp</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.340/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>7839</start>
<end>7860</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs
%A Wang, Liang
%A Mou, Xinyi
%A Liu, Xiaoyou
%A Huang, Xuanjing
%A Wei, Zhongyu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wang-etal-2026-curp
%X User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation with Large Language Models (LLMs) in contemporary approaches. However, existing methods, whether personalized prompt-based or parameter-based methods, face challenges in balancing personalization quality against computational and data efficiency. We propose a novel framework CURP, which employs a bidirectional user encoder, a discrete prototype codebook and a dual-aggregator to extract both multi-dimensional user traits and query-aware user characteristic. This design enables plug-and-play personalization with a small number of trainable parameters (about 28M parameters, about 0.36% of the total model size). Through extensive experiments, we show that CURP achieves superior performance and generalization compared to strong baselines on the language model personalization (LaMP) benchmark, while offering better interpretability and robustness.
%U https://aclanthology.org/2026.emnlp-main.340/
%P 7839-7860
Markdown (Informal)
[CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs](https://aclanthology.org/2026.emnlp-main.340/) (Wang et al., EMNLP 2026)
ACL