arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.11528cs.AI
收藏

个性化大语言模型综述:进展与未来方向

A Survey of Personalized Large Language Models: Progress and Future Directions

The Chinese University of Hong Kong(香港中文大学);Huawei Technologies Co., Ltd(华为技术有限公司);The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));National University of Singapore(新加坡国立大学)

Jiahong Liu, Zexuan Qiu, Zhongyang Li, Quanyu Dai, Wenhao Yu, Jieming Zhu, Minda Hu, Menglin Yang, Tat-Seng Chua, Irwin King

AI总结:

本文从输入提示、模型微调和目标对齐三个层面系统综述了个性化大语言模型的研究进展,并探讨了当前局限与未来方向。

摘要:

大语言模型(LLMs)在处理通用知识任务方面表现出色,但在用户特定的个性化方面仍面临困难,例如理解个人情绪、写作风格和偏好。个性化大语言模型(PLLMs)通过利用个体用户数据(如用户画像、历史对话、内容和交互记录)来应对这些挑战,从而提供与上下文相关且针对每个用户具体需求定制的回复。这是一个极具价值的研究课题,因为PLLMs能够显著提升用户满意度,并在对话智能体、推荐系统、情绪识别、医疗助手等领域具有广泛应用。本综述从三个技术视角回顾了PLLMs的最新进展:面向个性化上下文的提示(输入层面)、面向个性化适配器的微调(模型层面)以及面向个性化偏好的对齐(目标层面)。为提供更深入的见解,我们还讨论了当前的局限性,并概述了若干有前景的未来研究方向。本综述的更新信息可在 https://github.com/JiahongLiu21/Awesome-Personalized-Large-Language-Models 获取。

英文摘要:

Large Language Models (LLMs) excel in handling general knowledge tasks, yet they struggle with user-specific personalization, such as understanding individual emotions, writing styles, and preferences. Personalized Large Language Models (PLLMs) tackle these challenges by leveraging individual user data, such as user profiles, historical dialogues, content, and interactions, to deliver responses that are contextually relevant and tailored to each user's specific needs. This is a highly valuable research topic, as PLLMs can significantly enhance user satisfaction and have broad applications in conversational agents, recommendation systems, emotion recognition, medical assistants, and more. This survey reviews recent advancements in PLLMs from three technical perspectives: prompting for personalized context (input level), finetuning for personalized adapters (model level), and alignment for personalized preferences (objective level). To provide deeper insights, we also discuss current limitations and outline several promising directions for future research. Updated information about this survey can be found at the https://github.com/JiahongLiu21/Awesome-Personalized-Large-Language-Models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑