Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Sichun, Deng, Guanzhi, Xu, Jian, Zhang, Xiaojie, Hou, Hanxu, Song, Linqi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912389509677056
author Luo, Sichun
Deng, Guanzhi
Xu, Jian
Zhang, Xiaojie
Hou, Hanxu
Song, Linqi
author_facet Luo, Sichun
Deng, Guanzhi
Xu, Jian
Zhang, Xiaojie
Hou, Hanxu
Song, Linqi
contents Personalization is a critical task in modern intelligent systems, with applications spanning diverse domains, including interactions with large language models (LLMs). Recent advances in reasoning capabilities have significantly enhanced LLMs, enabling unprecedented performance in tasks such as mathematics and coding. However, their potential for personalization tasks remains underexplored. In this paper, we present the first systematic evaluation of large reasoning models (LRMs) for personalization tasks. Surprisingly, despite generating more tokens, LRMs do not consistently outperform general-purpose LLMs, especially in retrieval-intensive scenarios where their advantages diminish. Our analysis identifies three key limitations: divergent thinking, misalignment of response formats, and ineffective use of retrieved information. To address these challenges, we propose Reinforced Reasoning for Personalization (\model), a novel framework that incorporates a hierarchical reasoning thought template to guide LRMs in generating structured outputs. Additionally, we introduce a reasoning process intervention method to enforce adherence to designed reasoning patterns, enhancing alignment. We also propose a cross-referencing mechanism to ensure consistency. Extensive experiments demonstrate that our approach significantly outperforms existing techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17571
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation
Luo, Sichun
Deng, Guanzhi
Xu, Jian
Zhang, Xiaojie
Hou, Hanxu
Song, Linqi
Computation and Language
Personalization is a critical task in modern intelligent systems, with applications spanning diverse domains, including interactions with large language models (LLMs). Recent advances in reasoning capabilities have significantly enhanced LLMs, enabling unprecedented performance in tasks such as mathematics and coding. However, their potential for personalization tasks remains underexplored. In this paper, we present the first systematic evaluation of large reasoning models (LRMs) for personalization tasks. Surprisingly, despite generating more tokens, LRMs do not consistently outperform general-purpose LLMs, especially in retrieval-intensive scenarios where their advantages diminish. Our analysis identifies three key limitations: divergent thinking, misalignment of response formats, and ineffective use of retrieved information. To address these challenges, we propose Reinforced Reasoning for Personalization (\model), a novel framework that incorporates a hierarchical reasoning thought template to guide LRMs in generating structured outputs. Additionally, we introduce a reasoning process intervention method to enforce adherence to designed reasoning patterns, enhancing alignment. We also propose a cross-referencing mechanism to ensure consistency. Extensive experiments demonstrate that our approach significantly outperforms existing techniques.
title Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation
topic Computation and Language
url https://arxiv.org/abs/2505.17571