RPM: Reasoning-Level Personalization for Black-Box Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kim, Jieyong, Kim, Tongyoung, Yoon, Soojin, Kim, Jaehyung, Lee, Dongha
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917300979892224
author Kim, Jieyong
Kim, Tongyoung
Yoon, Soojin
Kim, Jaehyung
Lee, Dongha
author_facet Kim, Jieyong
Kim, Tongyoung
Yoon, Soojin
Kim, Jaehyung
Lee, Dongha
contents While black-box large language models are widely deployed, they produce generic outputs that overlook individual user preferences. Current personalization methods are fundamentally limited to response-level personalization; they only match final outputs, failing to model the underlying reasoning that connects user behavior to responses. To address this, this work introduces reasoning-level personalization as a new paradigm and proposes RPM, the first systematic framework that automatically discovers user-specific reasoning structures from raw behavioral data to guide the model's personalized inference. RPM constructs a structured model of user behavior-built from response-influential features and statistical factors-to create personalized reasoning paths and retrieve beneficial examples for guiding inference through a feature-based retrieval mechanism. Extensive experiments across four diverse tasks demonstrate that RPM consistently outperforms existing response-level methods while simultaneously enhancing both personalization performance and interpretability, providing a promising direction for black-box LLM personalization.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21082
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RPM: Reasoning-Level Personalization for Black-Box Large Language Models
Kim, Jieyong
Kim, Tongyoung
Yoon, Soojin
Kim, Jaehyung
Lee, Dongha
Computation and Language
While black-box large language models are widely deployed, they produce generic outputs that overlook individual user preferences. Current personalization methods are fundamentally limited to response-level personalization; they only match final outputs, failing to model the underlying reasoning that connects user behavior to responses. To address this, this work introduces reasoning-level personalization as a new paradigm and proposes RPM, the first systematic framework that automatically discovers user-specific reasoning structures from raw behavioral data to guide the model's personalized inference. RPM constructs a structured model of user behavior-built from response-influential features and statistical factors-to create personalized reasoning paths and retrieve beneficial examples for guiding inference through a feature-based retrieval mechanism. Extensive experiments across four diverse tasks demonstrate that RPM consistently outperforms existing response-level methods while simultaneously enhancing both personalization performance and interpretability, providing a promising direction for black-box LLM personalization.
title RPM: Reasoning-Level Personalization for Black-Box Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2505.21082