As large language models (LLMs) are progressively deployed in various real-world applications, personalization of LLMs has become increasingly important. While various approaches to LLM personalization such as prompt-based and training-based methods have been actively explored, the development of effective decoding-time algorithms remains largely overlooked, despite their demonstrated potential. In this paper, we propose CoPe (Contrasting Personal Preference), a novel decoding-time approach applied after performing parameter-efficient fine-tuning (PEFT) on user-specific data. Our core idea is to leverage reward-guided decoding specifically for personalization by maximizing each user's implicit reward signal. We evaluate CoPe across five open-ended personalized text generation tasks. Our empirical results demonstrate that CoPe achieves strong performance, improving personalization by an average of 10.57% in ROUGE-L, without relying on external reward models or additional training procedures.
@article{arxiv.2506.12109,
title = {Personalized LLM Decoding via Contrasting Personal Preference},
author = {Hyungjune Bu and Chanjoo Jung and Minjae Kang and Jaehyung Kim},
journal= {arXiv preprint arXiv:2506.12109},
year = {2025}
}