Recent advancements in large language models (LLMs) have indeed showcased their impressive capabilities. On mobile devices, the wealth of valuable, non-public data generated daily holds great promise for locally fine-tuning personalized LLMs, while maintaining privacy through on-device processing. However, the constraints of mobile device resources pose challenges to direct on-device LLM fine-tuning, mainly due to the memory-intensive nature of derivative-based optimization required for saving gradients and optimizer states. To tackle this, we propose employing derivative-free optimization techniques to enable on-device fine-tuning of LLM, even on memory-limited mobile devices. Empirical results demonstrate that the RoBERTa-large model and OPT-1.3B can be fine-tuned locally on the OPPO Reno 6 smartphone using around 4GB and 6.5GB of memory respectively, using derivative-free optimization techniques. This highlights the feasibility of on-device LLM fine-tuning on mobile devices, paving the way for personalized LLMs on resource-constrained devices while safeguarding data privacy.
Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；State Key Laboratory of General Artificial Intelligence, BIGAI（北京通用人工智能研究院通用人工智能国家重点实验室）；Shanghai Jiao Tong University（上海交通大学）；Zhongguancun Academy（中关村学院）
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院 Gallagher 学院）；Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（下一代智能搜索与推荐工程研究中心，教育部）；Baidu Inc.（百度公司）
Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis
Department of Electrical and Computer Engineering, Seoul National University（电子与计算机工程系，首尔国立大学）；Interdisciplinary Program in Artificial Intelligence, Seoul National University（人工智能跨学科计划，首尔国立大学）；AIIS, ASRI, INMC, and ISRC, Seoul National University（人工智能研究所、人工智能研究机构、智能网络中心和智能系统研究组，首尔国立大学）
Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment
College of Intelligence and Computing, Tianjin University, Tianjin, China（智能与计算学院，天津大学，天津，中国）；College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学，新加坡）
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学首都人工智能学院）；AI Lab at Lenovo Research（联想研究院人工智能实验室）；School of Artificial Intelligence and Data Science, University of International Business and Economics（国际商务与经济大学人工智能与数据科学学院）
Review-LLM: Harnessing Large Language Models for Personalized Review Generation
School of New Media Communication, Tianjin University（天津大学新媒体与传播学院）；Du Xiaoman Financial（度小满金融）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models
University of California, San Diego（加利福尼亚大学圣地亚哥分校）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Adobe Research（奥多比研究院）；The Ohio State University（俄亥俄州立大学）；Allen Institute for AI（艾伦人工智能研究所）
PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counseling
School of Future Technology, South China University of Technology（华南理工大学未来技术学院）；School of Electronic and Information Engineering, South China University of Technology（华南理工大学电子与信息工程学院）；Pazhou Lab（琶洲实验室）
Personalization of Large Language Models: A Survey
Dartmouth College（达特茅斯学院）；Adobe Research（Adobe研究）；Stanford University（斯坦福大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Pattern Data；Vanderbilt University（范德比尔特大学）；Dolby Research（Dolby研究）；University of California San Diego（加州大学圣地亚哥分校）；Cisco Research（思科研究）；University of Oregon（俄勒冈大学）
The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses
Warsaw University of Technology（华沙理工大学）；University of Warsaw（华沙大学）
Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription
Qatar University（卡塔尔大学）；Birmingham City University（伯明翰城市大学）；Hamad Bin Khalifa University (HBKU)（哈马德·本·哈利法大学）；University of the West of England (UWE)（西英格兰大学）
A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications
Ant Group（蚂蚁集团）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）
From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
PEToolLLM: Towards Personalized Tool Learning in Large Language Models
The Hong Kong Polytechnic University（香港理工大学）；National University of Singapore（新加坡国立大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations
University of Southern California（南加州大学）；Adobe Research（Adobe研究院）；University of California, San Diego（加州大学圣地亚哥分校）；Intel AI Research（英特尔人工智能研究）；University of Maryland, College Park（马里兰大学学院市分校）；Vanderbilt University（范德比大学）；Virginia Polytechnic Institute and State University（弗吉尼亚理工学院和州立大学）；University of Notre Dame（诺特丹大学）；University of Oregon（俄勒冈大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Arizona State University（亚利桑那州立大学）
