XAI for Transformers: Better Explanations through Conservative Propagation
Tel-Aviv University(特拉维夫大学);Technische Universität Berlin(柏林工业大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(BIFOLD——柏林学习与数据基础研究所);Korea University(高丽大学);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)
Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, Lior Wolf
Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transparency. Multiple interpretability methods, often based on gradient information, have been proposed. We show that the gradient in a Transformer reflects the function only locally, and thus fails to reliably identify the contribution of input features to the prediction. We identify Attention Heads and LayerNorm as main reasons for such unreliable explanations and propose a more stable way for propagation through these layers. Our proposal, which can be seen as a proper extension of the well-established LRP method to Transformers, is shown both theoretically and empirically to overcome the deficiency of a simple gradient-based approach, and achieves state-of-the-art explanation performance on a broad range of Transformer models and datasets.
PREF-XAI: Preference-Based Personalized Rule Explanations of Black-Box Machine Learning Models
University of Catania, Department of Economics and Business(卡塔尼亚大学经济与商业系);Poznan University of Technology, Institute of Computing Science(波兹南技术大学计算科学研究所);Systems Research Institute, Polish Academy of Sciences(波兰科学院系统研究所)
Beyond single-model XAI: aggregating multi-model explanations for enhanced trustworthiness
Department of Mathematics, Informatics and Geosciences, University of Trieste, Trieste, Italy(数学、信息学与地球科学系,特里埃斯特大学,特里埃斯特,意大利);The Abdus Salam International Center for Theoretical Physics, Trieste, Italy(阿布杜斯·萨拉姆国际理论物理中心,特里埃斯特,意大利)
Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy
Technische Universität Berlin(柏林工业大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(柏林学习与数据基础研究所);Fraunhofer Heinrich Hertz Institute(弗劳恩霍夫海因里希·赫兹研究所);Korea University(高丽大学);Max Planck Institut für Informatik(马克斯·普朗克信息学研究所)
Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement
Fraunhofer Heinrich Hertz Institute(弗劳恩霍夫海因里希·赫兹研究所);Singapore Institute of Technology(新加坡理工大学);University of Oslo(奥斯陆大学);Berlin Institute for the Foundations of Learning and Data(柏林学习与数据基础研究所)
On the Hardness of Computing Counterfactual and Semifactual Explanations in XAI
Faculty of Technology(技术学院);Bielefeld University(比勒菲尔德大学);Department of Business Development and Technology(商业发展与技术系);Aarhus University(哥本哈根大学);Department of Business Decisions and Analytics(商业决策与分析系);University of Vienna(维也纳大学)
TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning
Faculty of Computer and Information Science, University of Ljubljana, Slovenia(卢布尔雅那大学计算机与信息科学学院);ICAM - Advanced Environmental Research Institute, West University of Timisoara, Romania(蒂米șoara西大学先进环境研究所);Department of Computer Science, West University of Timisoara, Romania(蒂米șoa拉西大学计算机科学系)
Explainable Artificial Intelligence (XAI) from a user perspective- A synthesis of prior literature and problematizing avenues for future research
LUT University(拉彭兰塔-拉赫蒂工业大学);Norwegian University of Science and Technology(挪威科技大学);SINTEF Digital(挪威科技工业研究院数字研究所)
系统性文献综述(SLR)的最终检索查询于2022年7月15日进行。最初,我们从Scopus和Web of Science数据库中提取了1707篇期刊和会议文章。然后应用纳入和排除标准,选择58篇文章进行SLR。研究结果显示了塑造AI解释的四个维度,即格式(解释表示格式),完整性(解释应包含所有必要的信息,包括补充信息),准确性(关于解释准确性的信息)和货币(解释应包含最近的信息)。此外,随着解释的自动表示,用户可以在需要时请求附加信息。我们还发现了XAI效应的五个维度:信任、透明度、可理解性、可用性和公平性。此外,我们调查了当前的知识,从选定的文章问题化未来的研究议程,随着可能的研究路径的研究问题。因此,XAI及其对用户行为可能产生的影响的综合框架已经开发出来。
Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction
Federal University of Pará (UFPA)(帕拉联邦大学);Federal Institute of Education, Science and Technology of Pará (IFPA)(帕拉联邦教育、科学和技术学院);Vale Institute of Technology (ITV DS)(淡水河谷技术研究院)
Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
Berlin Institute for the Foundations of Learning(柏林学习与数据基础研究所);Machine Learning Group, Technical University of Berlin(柏林技术大学机器学习组);Department of Artificial Intelligence, Korea University(韩国大学人工智能系);Department of Mathematics and Computer Science, Free University of Berlin(柏林自由大学数学与计算机科学系)
Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefer
School of Computer Science, University College Dublin, Dublin, Ireland(都柏林大学计算机科学学院);Insight Research Ireland Centre for Data Analytics, Dublin, Ireland(爱尔兰洞察研究数据分析中心)
Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration
University of Ioannina(伊奥安纳大学);Archimedes / Athena RC Greece(阿基米德/亚特兰蒂斯研究所以及希腊);Freie Universität Berlin(柏林自由大学);Universität der Bundeswehr München(联邦国防军大学慕尼黑)
Optimizing Explanations by Network Canonization and Hyperparameter Search
Fraunhofer Heinrich-Hertz-Institute(弗劳恩霍夫海因里希·赫兹研究所);Technische Universität Berlin(柏林工业大学);Singapore Institute of Technology(新加坡理工学院);University of Oslo(奥斯陆大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(BIFOLD——柏林学习与数据基础研究所)
Extracting human interpretable structure-property relationships in chemistry using XAI and large language models
Laboratory of Artificial Chemical Intelligence(人工智能化学智能实验室);Institute of Chemical Sciences and Engineering(化学科学与工程研究所);Ecole Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院)
Mind the XAI Gap: A Human-Centered LLM Framework for Democratizing Explainable AI
Aristotle University of Thessaloniki, School of Informatics(塞萨洛尼基亚里士多德大学信息学院);Technical University of Denmark(丹麦技术大学);Telefonica Scientific Research(电信科学研究院)
Minimizing False-Positive Attributions in Explanations of Non-Linear Models
Technical University of Denmark(丹麦技术大学);Technische Universität Berlin(柏林技术大学);Physikalisch-Technische Bundesanstalt, Berlin(柏林物理技术部);Charité – Universitätsmedizin Berlin(柏林查理医院大学医学中心)
Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science
Technische Universität Berlin(柏林工业大学);ATB(莱布尼茨农业工程与生物经济研究所);University of Leipzig(莱比锡大学);University of Reading(雷丁大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(柏林学习与数据基础研究所(BIFOLD));UiT the Arctic University of Norway(挪威北极大学);University of Potsdam(波茨坦大学)