Large language models (LLMs) are trained on web-scale corpora that exhibit steep power-law distributions, in which the distribution of knowledge is highly long-tailed, with most appearing infrequently. While scaling has improved average-case performance, persistent failures on low-frequency, domain-specific, cultural, and temporal knowledge remain poorly characterized. This paper develops a structured taxonomy and analysis of long-Tail Knowledge in large language models, synthesizing prior work across technical and sociotechnical perspectives.
We introduce a structured analytical framework that synthesizes prior work across four complementary axes: how long-Tail Knowledge is defined, the mechanisms by which it is lost or distorted during training and inference, the technical interventions proposed to mitigate these failures, and the implications of these failures for fairness, accountability, transparency, and user trust. We further examine how existing evaluation practices obscure tail behavior and complicate accountability for rare but consequential failures. The paper concludes by identifying open challenges related to privacy, sustainability, and governance that constrain long-Tail Knowledge representation. Taken together, this paper provides a unifying conceptual framework for understanding how long-Tail Knowledge is defined, lost, evaluated, and manifested in deployed language model systems.
When AI Fails, What Works? A Data-Driven Taxonomy of Real-World AI Risk Mitigation Strategies
Faculty of Computer Science and Engineering（计算机科学与工程系）；Ss. Cyril and Methodius University（西里尔和方法ius大学）；Department of Computer Science（计算机科学系）；Metropolitan College（Metropolitan学院）
Towards Compositional Generalization of LLMs via Skill Taxonomy Guided Data Synthesis
State Key Laboratory of Complex & Critical Software Environment, Beihang University（复杂与关键软件环境国家重点实验室，北京航空航天大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Beijing Institute of Technology（北京理工大学）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）
Charting the European LLM Benchmarking Landscape: A New Taxonomy and a Set of Best Practices
Jožef Stefan Institute（乔塞夫·斯塔芬研究所）；University of Ljubljana（卢布尔雅那大学）；Faculty of Arts, University of Ljubljana（艺术学院，卢布尔雅那大学）；Faculty of Computer and Information Science, University of Ljubljana（计算机与信息科学学院，卢布尔雅那大学）；Institute of Contemporary History（现代史研究所）
Wearable Meets LLM for Stress Management: A Duoethnographic Study Integrating Wearable-Triggered Stressors and LLM Chatbots for Personalized Interventions
University of Memphis（孟菲斯大学）；Virginia Tech（弗吉尼亚理工大学）
What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct
Carnegie Mellon University（卡内基梅隆大学）；University of Oxford（牛津大学）；University of Toronto（多伦多大学）；Stanford University（斯坦福大学）；University of Cincinnati（克里夫兰医学中心大学）；New York University（纽约大学）
Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs
Department of Computer Science, Université Paris-Dauphine（巴黎-索邦大学计算机科学系）；Institute of Mathematics, EPFL（苏黎世联邦理工学院数学研究所）；Computational Engineering Lab, Empa（Empa计算工程实验室）
Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey
Archimedes, Athena Research Center（阿希米德研究中心）；Athens University of Economics and Business（雅典经济与商业大学）；École Normale Supérieure Paris-Saclay（巴黎萨克雷高等师范学校）；INSEAD
Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；JD Technology（京东科技）；JD Intelligent Cities Research（京东智能城市研究院）；Tsinghua University（清华大学）；Southwest Jiaotong University（西南交通大学）
Distorted or Fabricated? A Survey on Hallucination in Video LLMs
Department of Electrical and Computer Engineering, Northeastern University（东北大学电气与计算机工程系）；Khoury College of Computer Science, Northeastern University（东北大学科赫里计算机科学学院）
