School of Computer Science, Fudan University（复旦大学计算机科学学院）；Tencent AI Lab（腾讯AI实验室）；Institute of Modern Languages and Linguistics, Fudan University（复旦大学现代语言与语言学研究所）
Ruotian Ma, Xiaolei Wang, Xin Zhou, Jian Li, Nan Du, Tao Gui, Qi Zhang, Xuanjing Huang
LLM-based Automatic Prompt Optimization, which typically utilizes LLMs as Prompt Optimizers to self-reflect and refine prompts, has shown promising performance in recent studies. Despite the success, the underlying mechanism of this approach remains unexplored, and the true effectiveness of LLMs as Prompt Optimizers requires further validation. In this work, we conducted a comprehensive study to uncover the actual mechanism of LLM-based Prompt Optimization. Our findings reveal that the LLM optimizers struggle to identify the true causes of errors during reflection, tending to be biased by their own prior knowledge rather than genuinely reflecting on the errors. Furthermore, even when the reflection is semantically valid, the LLM optimizers often fail to generate appropriate prompts for the target models with a single prompt refinement step, partly due to the unpredictable behaviors of the target models. Based on the observations, we introduce a new "Automatic Behavior Optimization" paradigm, which directly optimizes the target model's behavior in a more controllable manner. We hope our study can inspire new directions for automatic prompt optimization development.
Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；International School, Beijing University of Posts and Telecommunications（北京邮电大学国际学院）；Alibaba Group（阿里巴巴集团）
Rethinking Prompt Optimizers: From Prompt Merits to Optimization
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（南洋理工大学电子与电气工程学院）；Home Team Science and Technology Agency, Singapore（新加坡科技局）
SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Hong Kong University of Science and Technology（香港科学与技术大学）；University of South Florida（佛罗里达州立大学）
How Should a Prompt Optimizer Spend a Tight Budget? BudgetAPO with Noise-Adaptive Evaluation
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen)（深圳市未来智联网络研究院）；Guangdong Provincial Key Laboratory of Future Networks of Intelligence, CUHK(SZ)（广东省未来智联网络重点实验室（香港中文大学（深圳）））
REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming
King Fahd University of Petroleum & Minerals（法赫德国王石油与矿产大学）；Imam Abdulrahman Bin Faisal University（伊玛目阿卜杜勒拉赫曼·本·费萨尔大学）；SDAIA-KFUPM Joint Research Center for Artificial Intelligence（SDAIA-KFUPM人工智能联合研究中心）
StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯AI实验室）
Large language models can perform new tasks in a zero-shot fashion, given natural language prompts that specify the desired behavior. Such prompts are typically hand engineered, but can also be learned with gradient-based methods from labeled data. However, it is underexplored what factors make the prompts effective, especially when the prompts are natural language. In this paper, we investigate common attributes shared by effective prompts. We first propose a human readable prompt tuning method (F LUENT P ROMPT) based on Langevin dynamics that incorporates a fluency constraint to find a diver…
Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers
Center for Information and Language Processing (CIS), LMU Munich（慕尼黑大学信息与语言处理中心（CIS））；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））；Amazon.com, Inc.（亚马逊公司）
promptolution: A Unified, Modular Framework for Prompt Optimization
ELLIS Institute（ELLIS研究所）；University of Freiburg（弗赖堡大学）；LMU Munich（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Technical University of Munich（慕尼黑技术大学）；TU Dortmund University（多特蒙德技术大学）；Lamarr Institute for Machine Learning and Artificial Intelligence（Lamarr机器学习与人工智能研究所）
National University of Singapore（国立新加坡大学）；Salesforce AI Research（Salesforce人工智能研究）；Institute for Infocomm Research (I 2 R), A*STAR（信息与通信研究 institute（I2R），A*STAR）
