Automatic Generation
Automatic generation encompasses the use of computational methods to create various forms of content, ranging from mathematical conjectures and software code to 3D game scenes and medical simulation scenarios. Current research focuses on leveraging large language models (LLMs) and other deep learning architectures, such as diffusion models and transformers, to generate diverse outputs, often guided by prompts or constraints derived from structured data or existing knowledge bases. This field is significant because it automates time-consuming and complex tasks, improving efficiency in diverse domains like software engineering, education, and healthcare, while also advancing our understanding of artificial intelligence and its capabilities.
Papers
Automated Generation of Massive Reasonable Empirical Theorems by Forward Reasoning Based on Strong Relevant Logics -- A Solution to the Problem of LLM Pre-training Data Exhaustion
Jingde Cheng
PROPOE 2: Avanços na Síntese Computacional de Poemas Baseados em Prosa Literária Brasileira
Felipe José D. Sousa, Sarah P. Cerqueira, João Queiroz, Angelo Loula