Facilitated by large language models (LLMs), personalized text generation has become a rapidly growing research direction. Most existing studies focus on designing specialized models for a particular domain, or they require fine-tuning the LLMs to generate personalized text. We consider a typical scenario in which the large language model, which generates personalized output, is frozen and can only be accessed through APIs. Under this constraint, all one can do is to improve the input text (i.e., text prompts) sent to the LLM, a procedure that is usually done manually. In this paper, we propose a novel method to automatically revise prompts for personalized text generation. The proposed method takes the initial prompts generated by a state-of-the-art, multistage framework for personalized generation and rewrites a few critical components that summarize and synthesize the personal context. The prompt rewriter employs a training paradigm that chains together supervised learning (SL) and reinforcement learning (RL), where SL reduces the search space of RL and RL facilitates end-to-end training of the rewriter. Using datasets from three representative domains, we demonstrate that the rewritten prompts outperform both the original prompts and the prompts optimized via supervised learning or reinforcement learning alone. In-depth analysis of the rewritten prompts shows that they are not only human readable, but also able to guide manual revision of prompts when there is limited resource to employ reinforcement learning to train the prompt rewriter, or when it is costly to deploy an automatic prompt rewriter for inference.
Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting
University of Oxford, Oxford, England(牛津大学);University of Berkeley, Berkeley, CA, USA(伯克利大学);Carnegie Mellon University, Pittsburgh, PA, USA(卡内基梅隆大学);Algoverse AI Research, Remote(Algoverse AI研究)
ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
Huazhong University of Science and Technology(华中科技大学);Huawei Noah’s Ark Lab(华为诺亚实验室);Hong Kong Polytechnic University(香港理工大学);Zhejiang University(浙江大学)
PersonaTwin: A Multi-Tier Prompt Conditioning Framework for Generating and Evaluating Personalized Digital Twins
Viterbi School of Engineering, University of Southern California(南加州大学维特比工程学院);Human-centered Analytics Lab, University of Notre Dame(诺特大学人本分析实验室);Department of IT, Analytics, and Operations, University of Notre Dame(诺特大学信息技术、分析与运营部门);Department of Information Systems, Business Statistics and Operations Management, HKUST(香港科技大学信息系统、商业统计与运营管理部门)
Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition
Graduate School of Information Science(信息科学研究生学校);Technology, Hokkaido University, Sapporo 060-0814, Japan(技术,北海道大学,札幌060-0814,日本);Office of Institutional Research, Hokkaido University, Sapporo 060-0808, Japan(机构研究办公室,北海道大学,札幌060-0808,日本);Faculty of Information Science(信息科学学院)
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)
Personalized Graph-Based Retrieval for Large Language Models
University of California Santa Cruz(加州大学圣克ruz分校);Meta AI;Adobe Research(Adobe研究);University of Oregon(俄勒冈大学);University of Southern California(南加州大学);Cisco AI Research(思科人工智能研究)
Which Client is Reliable?: A Reliable and Personalized Prompt-based Federated Learning for Medical Image Question Answering
Graduate School of Information Science and Technology, Hokkaido University(北海道大学信息科学与技术研究院);Faculty of Information Science and Technology, Hokkaido University(北海道大学信息科学与技术学院)
RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Peking University(北京大学);Kuaishou Technology(快手科技);Unaffliated(无所属机构)
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)