Comprehensive Taxonomy
Comprehensive taxonomies organize complex domains into hierarchical structures, aiming to clarify relationships between concepts and facilitate knowledge discovery and application. Current research focuses on developing and refining taxonomies across diverse fields, including natural language processing, computer vision, and machine learning, often leveraging large language models and advanced algorithms to automate the process and improve accuracy. These efforts are significant because well-structured taxonomies improve the efficiency of research, enhance the interpretability of complex models, and enable the development of more robust and reliable applications in various domains.
Papers
Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model
Fei Xia, Yixuan Weng, Shizhu He, Kang Liu, Jun Zhao
Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights
Hao Yang, Lizhen Qu, Ehsan Shareghi, Gholamreza Haffari
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
Nahema Marchal, Rachel Xu, Rasmi Elasmar, Iason Gabriel, Beth Goldberg, William Isaac
Towards Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models
Akchay Srivastava, Atif Memon