Explainability for Large Language Models (LLMs) is a critical yet challenging aspect of natural language processing. As LLMs are increasingly integral to diverse applications, their "black-box" nature sparks significant concerns regarding transparency and ethical use. This survey underscores the imperative for increased explainability in LLMs, delving into both the research on explainability and the various methodologies and tasks that utilize an understanding of these models. Our focus is primarily on pre-trained Transformer-based LLMs, such as LLaMA family, which pose distinctive interpretability challenges due to their scale and complexity. In terms of existing methods, we classify them into local and global analyses, based on their explanatory objectives. When considering the utilization of explainability, we explore several compelling methods that concentrate on model editing, control generation, and model enhancement. Additionally, we examine representative evaluation metrics and datasets, elucidating their advantages and limitations. Our goal is to reconcile theoretical and empirical understanding with practical implementation, proposing exciting avenues for explanatory techniques and their applications in the LLMs era.
Explainability for Large Language Models: A Survey
New Jersey Institute of Technology(新泽西理工学院);Johns Hopkins University(约翰斯·霍普金斯大学);Wake Forest University(维克森林大学);University of Georgia(佐治亚大学);Shanghai Jiao Tong University(上海交通大学);Institute of Computing Technology, CAS(中国科学院计算技术研究所);Baidu Inc.(百度公司);Rice University(莱斯大学)
Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
Virelya Intelligence Research Labs(Virelya智能研究实验室);Google(谷歌)
Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);Shanghai AI Laboratory(上海人工智能实验室);Nanyang Technological University(南洋理工大学);Renmin University of China(中国人民大学)
Reasoning LLMs in the Medical Domain: A Literature Survey
Fraunhofer IAIS - Department of Media Engineering(弗劳恩霍夫研究所媒体工程部门);University of Bonn - Department of Computer Science(波恩大学计算机科学系);West-AI - Federal Ministry of Education and Research(西德人工智能 - 教育与研究部)
Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization
School of Computer Science and Technology, HUST(华中科技大学计算机科学与技术学院);Faculty of Artificial Intelligence in Education, Central China Normal University(华中师范大学人工智能教育学部);iWudao Tech(悟道科技);School of Artificial Intelligence and Automation, HUST(华中科技大学人工智能与自动化学院)
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
Northwestern University(西北大学);New Jersey Institute of Technology(新泽西理工学院);University of Bristol(布里斯托大学);Cisco Research(思科研究);University of Illinois Chicago(伊利诺伊大学芝加哥分校)
TSXplain: Demystification of DNN Decisions for Time-Series using Natural Language and Statistical Features
Technische Universität Kaiserslautern(凯泽斯劳滕工业大学);German Research Center for Artificial Intelligence (DFKI) GmbH(德国人工智能研究中心(DFKI)有限公司);IAV GmbH(IAV有限公司)