Generative LLM
Generative Large Language Models (LLMs) are a class of AI models designed to produce human-quality text and other data formats. Current research focuses on improving their efficiency (through hardware acceleration and optimized algorithms), enhancing their capabilities (via techniques like instruction fine-tuning and data augmentation), and mitigating limitations such as memorization and biases. These advancements are driving significant progress in various fields, including natural language processing, materials science, and healthcare, by automating tasks, improving data analysis, and enabling new forms of human-computer interaction.
Papers
Efficient Prompting for LLM-based Generative Internet of Things
Bin Xiao, Burak Kantarci, Jiawen Kang, Dusit Niyato, Mohsen Guizani
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
Abhimanyu Hans, Yuxin Wen, Neel Jain, John Kirchenbauer, Hamid Kazemi, Prajwal Singhania, Siddharth Singh, Gowthami Somepalli, Jonas Geiping, Abhinav Bhatele, Tom Goldstein