paper-with-me

Papers

PrefReward: Learning User Preference Matrix for Personalized Text Generation

2026-07-23 · Yue Wu, Chengbing Wang, Yimeng Bai, Xiaoyan Zhao, Yang Zhang, Fuli Feng arxiv

Large Language Models (LLMs) have demonstrated remarkable ability in generating personalized content by leveraging user histories and contextual cues. However, most existing personalization approaches rely on implicit representations within model parameters, making it difficult to interpret user-specific preferences or effectively handle long-context dependencies. To address these challenges, we propose PrefReward, a novel preference-aware generative framework that explicitly models user styles through a structured preference matrix and integrates it into the decoding process as a reward signal. PrefReward consists of two stages: (1) extracting a user-specific preference matrix that summarizes individual stylistic tendencies, and (2) using the matrix to guide generation via a KL-divergence-based reward function. Experiments on the LongLaMP dataset show that PrefReward outperforms non-personalized and retrieval-based baselines in both generation quality and personalization interpretability.

📄 PDF Abstract BibTeX arXiv:2607.21067

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Quantum Recommendation Systems

2016-09-22 · Kerenidis Iordanis, Prakash Anupam

A recommendation system uses the past purchases or ratings of $n$ products by a group of $m$ users, in order to provide personalized recommendations to individual users. The information is modeled as an $m \times n$ pref…

Quantum Machine LearningRecommendation Systems

Real-Time Personalized Content Adaptation through Matrix Factorization and Context-Aware Federated Learning

2025-11-23 · Sai Puppala, Ismail Hossain, Md Jahangir Alam, Sajedul Talukder arxiv

Our study presents a multifaceted approach to enhancing user interaction and content relevance in social media platforms through a federated learning framework. We introduce personalized LLM Federated Learning and Contex…

Federated Learning

Personalized Language Modeling from Personalized Human Feedback

2024-02-06 · Xinyu Li, Ruiyang Zhou, Zachary C. Lipton, Liu Leqi

Personalized large language models (LLMs) are designed to tailor responses to individual user preferences. While Reinforcement Learning from Human Feedback (RLHF) is a commonly used framework for aligning LLMs with human…

Instruction FollowingLanguage ModelingLanguage ModellingPreference Mapping+1

Inference-Time Personalized Alignment with a Few User Preference Queries

2025-11-04 · Victor-Alexandru Pădurean, Parameswaran Kamalaruban, Nachiket Kotalwar, Alkis Gotovos 외 arxiv

We study the problem of aligning a generative model's response with a user's preferences. Recent works have proposed several different formulations for personalized alignment; however, they either require a large amount …

Image Generation

Fine-Grained User Profiling for Personalized Task Matching in Mobile Crowdsensing

2018-11-14 · Yang Shuo, Zheng Zhenzhe, Tang Shaojie, Wu Fan 외

In mobile crowdsensing, finding the best match between tasks and users is crucial to ensure both the quality and effectiveness of a crowdsensing system. Existing works usually assume a centralized task assignment by the …

Recommendation Systems