paper-with-me

Papers

CoPL: Collaborative Preference Learning for Personalizing LLMs

2025-03-03 · Youngbin Choi, Seunghyuk Cho, Minjong Lee, Moonjeong Park, Yesong Ko, Jungseul Ok, Dongwoo Kim

Personalizing large language models (LLMs) is important for aligning outputs with diverse user preferences, yet existing methods struggle with flexibility and generalization. We propose CoPL (Collaborative Preference Learning), a graph-based collaborative filtering framework that models user-response relationships to enhance preference estimation, particularly in sparse annotation settings. By integrating a mixture of LoRA experts, CoPL efficiently fine-tunes LLMs while dynamically balancing shared and user-specific preferences. Additionally, an optimization-free adaptation strategy enables generalization to unseen users without fine-tuning. Experiments on UltraFeedback-P demonstrate that CoPL outperforms existing personalized reward models, effectively capturing both common and controversial preferences, making it a scalable solution for personalized LLM alignment.

📄 PDF Abstract BibTeX arXiv:2503.01658

Code (0)

등록된 구현이 없습니다.

Tasks

Collaborative Filtering

Similar Papers 제목 키워드 기반

LoRe: Personalizing LLMs via Low-Rank Reward Modeling

2025-04-20 · Avinandan Bose, Zhihan Xiong, Yuejie Chi, Simon Shaolei Du 외

Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning from human feedback (RLHF) approaches ofte…

Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment

2024-12-30 · Jianfei Zhang, Jun Bai, Bei Li, Yanmeng Wang 외

Aligning Large Language Models (LLMs) with general human preferences has been proved crucial in improving the interaction quality between LLMs and human. However, human values are inherently diverse among different indiv…

Text Generation

Beyond BEV: Optimizing Point-Level Tokens for Collaborative Perception

2025-08-27 · Yang Li, Quan Yuan, Guiyang Luo, Xiaoyuan Fu 외 arxiv

Collaborative perception allows agents to enhance their perceptual capabilities by exchanging intermediate features. Existing methods typically organize these intermediate features as 2D bird's-eye-view (BEV) representat…

Object Recognition

LiteraryTaste: A Preference Dataset for Creative Writing Personalization

2025-11-12 · John Joon Young Chung, Vishakh Padmakumar, Melissa Roemmele, Yi Wang 외 arxiv

People have different creative writing preferences, and large language models (LLMs) for these tasks can benefit from adapting to each user's preferences. However, these models are often trained over a dataset that consi…

Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework

2026-05-11 · Xilai Ma, Liye Zhao, Weijun Yao, Haibing Di 외 arxiv

Large Language Model (LLM) personalization aims to align model behaviors with individual user preferences. Existing methods often focus on isolated user histories, neglecting the essential role of inter-user differences.…