With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning regards selecting appropriate keywords included into the input, thereby adapting to the downstream task without adjusting or fine-tuning the model parameters. There is a wide range of work in prompt tuning, from approaches that directly harness the backpropagated gradient signals from the model, to those employing black-box optimization such as reinforcement learning (RL) methods. Our primary focus is on RLPrompt, which aims to find optimal prompt tokens leveraging soft Q-learning. While the results show promise, we have observed that the prompts frequently appear unnatural, which impedes their interpretability. We address this limitation by using sparse Tsallis entropy regularization, a principled approach to filtering out unlikely tokens from consideration. We extensively evaluate our approach across various tasks, including few-shot text classification, unsupervised text style transfer, and textual inversion from images. The results indicate a notable improvement over baselines, highlighting the efficacy of our approach in addressing the challenges of prompt tuning. Moreover, we show that the prompts discovered using our method are more natural and interpretable compared to those from other baselines.
IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector
Computer Science and Engineering, Hong Kong University of Science and Technology（香港科技大学计算机科学与工程学院）；School of Computing and Data Science, The University of Hong Kong（香港大学计算机科学与数据科学学院）；School of Information Science & Engineering, Lanzhou University（兰州大学信息科学与工程学院）；Max Planck Institute for Security and Privacy（安全与隐私研究所）；Computer Science, The University of Michigan（密歇根大学计算机科学系）；Center for Data Science, Peking University（北京大学数据科学中心）
iPOE: Interpretable Prompt Optimization via Explanations
Fundamentals of Natural Language Processing, University of Bamberg, Germany（自然语言处理基础，巴姆堡大学，德国）；Leibniz-Institut für Psychologie (ZPID), Trier, Germany（莱比锡心理学研究所（ZPID），特里尔，德国）
Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer
Department of Electrical and Computer Engineering（电气与计算机工程系）；Duke University（杜克大学）；Department of Biostatistics and Bioinformatics（生物统计学与生物信息学系）；Department of Computer Science（计算机科学系）
Towards Interpretable Mental Health Analysis with Large Language Models
The University of Manchester（曼彻斯特大学）；University of Helsinki（赫尔辛基大学）；Yale University（耶鲁大学）；Artificial Intelligence Research Center, AIST（日本国立研究开发法人产业技术综合研究所人工智能研究中心）；Jiangxi Normal University（江西师范大学）
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）
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
University of California, Berkeley（加州大学伯克利分校）；University of Washington（华盛顿大学）；Duke University（杜克大学）；Carnegie Mellon University（卡内基梅隆大学）；Stanford University（斯坦福大学）
Improving LLM Reasoning through Interpretable Role-Playing Steering
Center for Information and Language Processing, LMU Munich（信息与语言处理中心，慕尼黑大学）；Northwestern University（西北大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））；New Jersey Institute of Technology（新泽西理工学院）
xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen University of Advanced Technology（深圳理工大学）；WUST（武汉科技大学）；HITSZ（哈尔滨工业大学（深圳））；School of Biomedical Engineering, UNSW Sydney（新南威尔士大学悉尼分校生物医学工程学院）
Learning Interpretable Shapelets for Time Series Classification through Adversarial Regularization
Univ Rennes（雷恩大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；IRISA（雷恩信息与随机系统研究所）；Laboratoire Hubert Curien UMR 5516（于贝尔·居里安实验室 UMR 5516）；Univ Lyon（里昂大学）；LETG（环境时空地理学实验室）
Interpretable Neuron Structuring with Graph Spectral Regularization
Yale Department of Computer Science（耶鲁大学计算机科学系）；Yale Department of Genetics（耶鲁大学遗传学系）；Université de Montréal, Dept. of Math. & Stat.（蒙特利尔大学数学与统计系）；Mila（米拉研究院）
Deep Relevance Regularization: Interpretable and Robust Tumor Typing of Imaging Mass Spectrometry Data
University of Bremen（不来梅大学）；SCiLS, Bruker Daltonik GmbH（布鲁克道尔顿公司SCiLS部门）；Proteopath GmbH（Proteopath公司）；Center for Histology Cytology and Molecular Diagnostic, Trier（特里尔组织学、细胞学与分子诊断中心）
Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control
Department of Computer Science（计算机科学系）；Indian Institute of Technology (ISM), Dhanbad（印度理工学院（ISM），丹巴德）；National University of Singapore（新加坡国立大学）；CIFAR Fellow（CIFAR研究员）
Interpretable Operator Learning for Inverse Problems via Adaptive Spectral Filtering: Convergence and Discretization Invariance
School of Instrumentation Science and Engineering, Harbin Institute of Technology（仪器科学与工程学院，哈尔滨工业大学）；School of Mathematics, Jilin University（吉林大学数学学院）；School of Mathematics, Inner Mongolia University（内蒙古大学数学学院）
