Fine-tuning is widely used to adapt language models for specific goals, often leveraging real-world data such as patient records, customer-service interactions, or web content in languages not covered in pre-training. These datasets are typically massive, noisy, and often confidential, making their direct inspection challenging. However, understanding them is essential for guiding model deployment and informing decisions about data cleaning or suppressing any harmful behaviors learned during fine-tuning. In this study, we introduce the task of novelty discovery through generation, which aims to identify novel properties of a fine-tuning dataset by generating examples that illustrate these properties. Our approach, Contrastive Generative Exploration (CGE), assumes no direct access to the data but instead relies on a pre-trained model and the same model after fine-tuning. By contrasting the predictions of these two models, CGE can generate examples that highlight novel characteristics of the fine-tuning data. However, this simple approach may produce examples that are too similar to one another, failing to capture the full range of novel phenomena present in the dataset. We address this by introducing an iterative version of CGE, where the previously generated examples are used to update the pre-trained model, and this updated model is then contrasted with the fully fine-tuned model to generate the next example, promoting diversity in the generated outputs. Our experiments demonstrate the effectiveness of CGE in detecting novel content, such as toxic language, as well as new natural and programming languages. Furthermore, we show that CGE remains effective even when models are fine-tuned using differential privacy techniques.
Sparse Reward Exploration via Novelty Search and Emitters
AI Lab, SoftBank Robotics Europe(软银机器人欧洲人工智能实验室);Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Institut des Systèmes Intelligents et de Robotique, ISIR(智能系统与机器人研究所)
AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing
Department of Physics, Massachusetts Institute of Technology(麻省理工学院物理系);The NSF AI Institute for Artificial Intelligence and Fundamental Interactions(国家科学基金会人工智能与基本相互作用研究所);Department of Physics, University of Wisconsin, Madison(威斯康星大学麦迪逊分校物理系)
FastFT: Accelerating Reinforced Feature Transformation via Advanced Exploration Strategies
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉科学学院);School of Computing and Information Technology, Great Bay University(大湾区大学计算与信息技术学院);Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局);Arizona State University(亚利桑那州立大学)
Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
Shanghai Jiao Tong University(上海交通大学);School of Automation and Intelligent Sensing(自动化与智能感知学院);Key Laboratory of System Control and Information Processing(系统控制与信息处理重点实验室);Ministry of Education of China(中华人民共和国教育部);National Key Laboratory of Human-Machine Hybrid Augmented Intelligence(人机混合增强智能国家级重点实验室);Institute of Artificial Intelligence and Robotics(人工智能与机器人研究院)
The Cyborg Astrobiologist: Testing a Novelty-Detection Algorithm on Two Mobile Exploration Systems at Rivas Vaciamadrid in Spain and at the Mars Desert Research Station in Utah
Freie Univ. Berlin(柏林自由大学);Centro de Astrobiología (CSIC/INTA)(天体生物学中心(西班牙国家研究委员会/西班牙航空航天技术研究所));McDonnell Center for the Space Sciences, Washington Univ.(华盛顿大学麦克唐纳空间科学中心);Univ. Malta(马耳他大学);Univ. Málaga(马拉加大学);ESTEC(欧洲空间研究与技术中心);Geological Survey of Spain (IGME)(西班牙地质调查局);Technische Fakultät, Univ. Bielefeld(比勒费尔德大学工程学院);IfG - Institute for Scientific Instruments GmbH(IfG科学仪器有限公司);Univ. Chicago(芝加哥大学)
在以前的工作中,已经开发了两个平台来测试机器人行星探索的计算机视觉算法(McGuire等人,2004 b,2005; Bartolo等人,2007)。可穿戴计算机平台已在西班牙的地质和天体生物学现场(Rivas Vaciamadrid和Riba de Euste)进行了测试,手机相机已在马耳他的地质现场进行了测试。在这项工作中,我们(i)应用Hopfield神经网络算法进行基于颜色的新颖性检测,(ii)在可穿戴计算机平台上集成一个现场数字显微镜,(iii)在Rivas Vaciamadrid使用数字显微镜测试这种新颖性检测,(iv)为手机相机平台开发蓝牙通信模式,以便允许访问现场的移动处理计算机,以及(v)在犹他州的火星沙漠研究站测试连接到上网本计算机的具有蓝牙功能的手机摄像头上的新奇检测。这种系统工程和现场测试一起使我们能够开发一种实时计算机视觉系统,该系统能够在半干旱沙漠环境中获得的一系列图像中识别地衣。我们获得了犹他州和西班牙地质露头的图像序列,包括各种岩石类型和颜色,以测试该算法。该算法通过颜色鲁棒地识别先前观察到的单元,同时只需要单个图像或几个图像就可以将颜色学习为熟悉的颜色,这证明了其快速学习能力。
Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
Engineering Research Center of Machine Learning and Industry Intelligence(机器学习与产业智能工程研究中心);National University of Singapore(新加坡国立大学);University of Leeds(利兹大学);Sichuan University(四川大学)
Towards Explainable, Safe Autonomous Driving with Language Embeddings for Novelty Identification and Active Learning: Framework and Experimental Analysis with Real-World Data Sets
University of California San Diego(加利福尼亚大学圣迭戈分校);Laboratory for Intelligent and Safe Automobiles(智能与安全汽车实验室)
ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods
Institute of AI for Health, Helmholtz Munich(亥姆霍兹慕尼黑人工智能健康研究所);School of Computation, Information and Technology, Technical University of Munich(慕尼黑技术大学计算、信息与技术学院);Helmholtz AI(亥姆霍兹人工智能研究所);Munich Center for Machine Learning(慕尼黑机器学习中心);Faculty of Mathematics, Informatics and Mechanics, University of Warsaw(华沙大学数学、信息学与力学学院)
Generative and multimodal AI for materials prediction and design: Progress, challenges, and perspectives
School of Computer Science, University of Sheffield, Sheffield, UK(计算机科学学院,谢菲尔德大学);Centre for Machine Intelligence, University of Sheffield, Sheffield, UK(智能机器研究中心,谢菲尔德大学);School of Chemical, Materials and Biological Engineering, University of Sheffield, Sheffield, UK(化学、材料与生物工程学院,谢菲尔德大学);Henry Royce Institute, Royce Discovery Centre, University of Sheffield, Sheffield, UK(亨利·罗伊奇研究所,谢菲尔德大学);Materials Nexus Ltd., Salisbury House, Cambridge, UK(材料 nexus 有限公司,剑桥,英国);School of Mathematical and Physical Sciences, University of Sheffield, Sheffield, UK(数学与物理科学学院,谢菲尔德大学)
MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies
LAION;University of California San Diego(加州大学圣迭戈分校);Mila, Quebec Artificial Intelligence Institute(Mila魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);University of Surrey(萨里大学)