From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Jia-Nan, Guan, Jian, Wu, Songhao, Wu, Wei, Yan, Rui
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913852910731264
author Li, Jia-Nan
Guan, Jian
Wu, Songhao
Wu, Wei
Yan, Rui
author_facet Li, Jia-Nan
Guan, Jian
Wu, Songhao
Wu, Wei
Yan, Rui
contents Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in user values and needs. This paper introduces a comprehensive framework for scalable personalized alignment of LLMs. We establish a systematic preference space characterizing psychological and behavioral dimensions, alongside diverse persona representations for robust preference inference in real-world scenarios. Building upon this foundation, we introduce \textsc{AlignX}, a large-scale dataset of over 1.3 million personalized preference examples, and develop two complementary alignment approaches: \textit{in-context alignment} directly conditioning on persona representations and \textit{preference-bridged alignment} modeling intermediate preference distributions. Extensive experiments demonstrate substantial improvements over existing methods, with an average 17.06\% accuracy gain across four benchmarks while exhibiting a strong adaptation capability to novel preferences, robustness to limited user data, and precise preference controllability. These results validate our approach toward user-adaptive AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15463
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
Li, Jia-Nan
Guan, Jian
Wu, Songhao
Wu, Wei
Yan, Rui
Computation and Language
Artificial Intelligence
Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in user values and needs. This paper introduces a comprehensive framework for scalable personalized alignment of LLMs. We establish a systematic preference space characterizing psychological and behavioral dimensions, alongside diverse persona representations for robust preference inference in real-world scenarios. Building upon this foundation, we introduce \textsc{AlignX}, a large-scale dataset of over 1.3 million personalized preference examples, and develop two complementary alignment approaches: \textit{in-context alignment} directly conditioning on persona representations and \textit{preference-bridged alignment} modeling intermediate preference distributions. Extensive experiments demonstrate substantial improvements over existing methods, with an average 17.06\% accuracy gain across four benchmarks while exhibiting a strong adaptation capability to novel preferences, robustness to limited user data, and precise preference controllability. These results validate our approach toward user-adaptive AI systems.
title From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.15463