Prompt tuning, in which prompts are optimized to adapt large-scale pre-trained language models to downstream tasks instead of fine-tuning the full model parameters, has been shown to be particularly effective when the prompts are trained in a multi-task transfer learning setting. These methods generally involve individually training prompts for each source task and then aggregating them to provide the initialization of the prompt for the target task. However, this approach critically ignores the fact that some of the source tasks could be negatively or positively interfering with each other. We argue that when we extract knowledge from source tasks via training source prompts, we need to consider this correlation among source tasks for better transfer to target tasks. To this end, we propose a Bayesian approach where we work with the posterior distribution of prompts across source tasks. We obtain representative source prompts corresponding to the samples from the posterior utilizing Stein Variational Gradient Descent, which are then aggregated to constitute the initial target prompt. We show extensive experimental results on the standard benchmark NLP tasks, where our Bayesian multi-task transfer learning approach outperforms the state-of-the-art methods in many settings. Furthermore, our approach requires no auxiliary models other than the prompt itself, achieving a high degree of parameter efficiency.
Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
Faculty of Information Technology, Brno University of Technology(布拉格技术大学信息学院);Kempelen Institute of Intelligent Technologies(智能技术研究所);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心)
Optimizing Soft Prompt Tuning via Structural Evolution
School of Information and Software Engineering, University of Electronic Science and Technology of China(电子科技大学信息与软件工程学院);School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院);College of Professional and Continuing Education, The Hong Kong Polytechnic University(香港理工大学专业及继续教育学院);School of Robotics and Advanced Manufacture, Harbin Institute of Technology(哈尔滨工业大学机器人与先进制造学院);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院)
Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach
Zhejiang University(浙江大学);Hangzhou YunQi Academy of Engineering(杭州云栖工程学院);College of Computer Science and Technology, Zhejiang University of Technology(浙江工业大学计算机科学与技术学院);Alibaba Cloud Computing(阿里巴巴云计算)
PromptEmbedder: Efficient and Transferable Text Embedding via Dual-LLM Soft Prompting
Department of Computer Science and Information Engineering, National Taiwan University(国立台湾大学计算机科学与资讯工程系);National Taiwan University AI Center of Research Excellence(国立台湾大学人工智能研究中心)
Sequential Bayesian Evaluation of Large Language Model Behavior
Department of Statistics, University of California, Irvine(统计系,加州大学伊文斯分校);Department of Computer Science, University of California, Irvine(计算机科学系,加州大学伊文斯分校)
Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning
School of Computer Science, Wuhan University(武汉大学计算机学院);National Engineering Research Center for Multimedia Software(国家多媒体软件工程技术研究中心);School of Electronic Information Engineering, Henan Polytechnic Institute(河南工业职业技术学院电子信息工程学院);JD Explore Academy(京东探索研究院)
Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
Chalmers University of Technology and University of Gothenburg, Sweden(楚姆勒大学技术学院和哥德堡大学,瑞典);Technical University of Denmark, Kgs. Lyngby, Denmark(丹麦技术大学,基斯勒吕辛,丹麦)
Unlocking Memorization in Large Language Models with Dynamic Soft Prompting
George Mason University(乔治梅森大学);GE Healthcare(GE医疗);University of Pittsburgh(匹兹堡大学);William and Mary(威廉玛丽学院);Southern University of Science and Technology(南方科技大学);Florida State University(佛罗里达州立大学)
Faculty of Information Technology, Brno University of Technology(布拉格技术大学信息学院);Kempelen Institute of Intelligent Technologies(智能技术研究所);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心)
Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models
National Key Laboratory of Radar Signal Processing, Xidian University(西安电子科技大学雷达信号处理国家重点实验室);McCombs School of Business, The University of Texas at Austin(德克萨斯大学奥斯汀分校麦库姆斯商学院)
Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI)(德国人工智能研究中心);Centre for European Research in Trusted AI (CERTAIN)(欧洲可信人工智能研究中心);sequire technology GmbH(sequire技术有限公司)
Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysis
Auckland University of Technology(奥克兰理工大学);University of Tasmania(塔斯马尼亚大学);Hefei University of Technology(合肥工业大学);Jilin University of Finance and Economics(吉林财经大学)
PromptAL: Sample-Aware Dynamic Soft Prompts for Few-Shot Active Learning
School of Cyberspace Security, Beijing University of Posts and Telecommunications(网络安全学院,北京邮电大学);Key Laboratory of Trustworthy Distributed Computing and Service (BUPT), Ministry of Education(可信分布式计算与服务重点实验室(北京邮电大学));QI-ANXIN Group(QI-ANXIN集团);RapidAI Research(RapidAI研究院);ZGC Lab(ZGC实验室)
MoPD: Mixture-of-Prompts Distillation for Vision-Language Models
Department of Computer Science and Engineering, Southern University of Science and Technology(计算机科学与工程系,南方科技大学);School of Mathematical and Computer Sciences, University of Adelaide(数学与计算机科学学院,阿德莱德大学)