We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model (e.g., T5) to generate an auxiliary directional stimulus prompt for each input instance. These directional stimulus prompts act as nuanced, instance-specific hints and clues to guide LLMs in generating desired outcomes, such as including specific keywords in the generated summary. Our approach sidesteps the challenges of direct LLM tuning by optimizing the policy model to explore directional stimulus prompts that align LLMs with desired behaviors. The policy model can be optimized through 1) supervised fine-tuning using labeled data and 2) reinforcement learning from offline or online rewards based on the LLM's output. We assess our method across summarization, dialogue response generation, and chain-of-thought reasoning tasks. Our experiments demonstrate that the framework consistently improves LLMs' (e.g., ChatGPT, Codex, InstructGPT) performance on these supervised tasks using minimal labeled data. Notably, using just 80 dialogues on the MultiWOZ dataset, our approach enhances ChatGPT's performance by an impressive 41.4%, matching or surpassing some fully supervised start-of-the-art models. Additionally, the instance-specific chain-of-thought prompt generated by our approach improves InstructGPT's reasoning accuracy compared to human-crafted or automatically generated prompts. The code and data are publicly available at \url{https://github.com/Leezekun/Directional-Stimulus-Prompting}.
SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine
International Digital Economy Academy（国际数字经济学院）；School of Software & Microelectronics, Peking University（北京大学软件与微电子学院）；National Key Laboratory for Multimedia Information Processing（多媒体信息处理国家重点实验室）；School of Computer Science, Peking University（北京大学计算机学院）；Data Science and Artificial Intelligence, Monash University（莫纳什大学数据科学与人工智能学院）；ModelTC
Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；Usher Institute, University of Edinburgh（爱丁堡大学厄舍研究所）；Edinburgh Futures Institute, University of Edinburgh（爱丁堡未来研究所）；School of Literatures, Languages and Cultures, University of Edinburgh（爱丁堡大学文学、语言与文化学院）
Guiding Language Models to Be More Empathetic: Culturally Sensitive Mental Health Advice Generation Through Human-LLM Collaboration
Ahsanullah University of Science and Technology（阿山努拉科技大学）；Bangladesh University of Business and Technology（孟加拉国商业与技术大学）；The University of New South Wales（新南威尔士大学）；Jashore University of Science and Technology（贾绍尔科技大学）；American International University - Bangladesh（孟加拉国美国国际大学）
Is ChatGPT a Good Personality Recognizer? A Preliminary Study
Institute of AI Education, East China Normal University（华东师范大学人工智能教育研究院）；School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；School of Psychology and Cognitive Science, East China Normal University（华东师范大学心理与认知科学学院）；Shanghai Changning Mental Health Center（上海市长宁区精神卫生中心）
Enhancing Depression Detection with Chain-of-Thought Prompting: From Emotion to Reasoning Using Large Language Models
College of Information Science and Engineering, Ritsumeikan University（立命馆大学信息科学与工程学院）；Fujita Health University（藤田医科大学）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）
LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
Shanghai Business School（上海商学院）；Learnable.AI Inc.（Learnable.AI公司）；Centre for Frontier AI Research, A*STAR（前沿人工智能研究中心，A*STAR）；Institute of High-Performance Computing, A*STAR（高性能计算研究所，A*STAR）；The Hong Kong Polytechnic University（香港理工大学）；Microsoft Research Asia（微软亚洲研究院）
From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory
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）；Meituan（美团）；Nanjing University of Posts and Telecommunications（南京邮电大学）；AI Centre, Department of Computer Science, University College London（伦敦大学学院计算机科学系人工智能中心）
Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation
Department of Methodology and Statistics, Utrecht University, The Netherlands（方法论与统计学系，乌特列支大学，荷兰）；Department of Information and Computing Sciences, Utrecht University, The Netherlands（信息与计算科学系，乌特列支大学，荷兰）；Queen Mary University of London, London, United Kingdom（伦敦女王玛丽大学，伦敦，英国）
Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
Department of Electrical and Computer Engineering, Seoul National University（电子与计算机工程系，首尔国立大学）；AIIS, ASRI, INMC, ISRC, and IPAI, Seoul National University（人工智能研究所、人工智能研究机构、智能网络中心、智能系统研究所以及人工智能与公共政策研究所，首尔国立大学）
Identifying Effective Strategies in Prompt Evolution for Stress and Emotion Prediction
Kyung Hee University（庆熙大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Graphen, Inc.（Graphen公司）；Vanderbilt University（范德堡大学）；Monroe Carell Jr. Children’s Hospital at Vanderbilt（范德堡大学门罗·卡雷尔 Jr.儿童医院）
Are LLMs effective psychological assessors? Leveraging adaptive RAG for interpretable mental health screening through psychometric practice
Euler Institute, Università della Svizzera italiana（欧拉研究所，瑞士大学）；National Institute of Informatics（国家信息研究所）；Brown University（布朗大学）；University of Tübingen（图宾根大学）；Insubria University（因斯布里亚大学）
Cognition Chain for Explainable Psychological Stress Detection on Social Media
University of Oxford（牛津大学）；Tsinghua University（清华大学）；Beijing Normal University（北京师范大学）；Wuhan University（武汉大学）；Oxford Suzhou Centre for Advanced Research（牛津苏州高等研究院）
