Revision Process
Revision processes, encompassing the updating of beliefs, models, or texts in response to new information or feedback, are a central focus across diverse scientific fields. Current research emphasizes developing efficient and accurate revision algorithms, often leveraging techniques like Control Barrier Functions for safety-critical systems, recurrent neural networks for temporal data, and large language models for text-based revisions. These advancements are improving the robustness and performance of autonomous systems, enhancing machine learning models, and facilitating more effective human-computer interaction in applications ranging from writing assistance to scientific publication editing.
Papers
Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain
Chunxi Guo, Zhiliang Tian, Jintao Tang, Shasha Li, Zhihua Wen, Kaixuan Wang, Ting Wang
System of Spheres-based Two Level Credibility-limited Revisions
Marco Garapa, Eduardo Ferme, Maurício D. L. Reis