Knowledge-Aware Learning Framework Based on Schema Theory to Complement Large Learning Models

• 成果类型: Article
• 署名作者: Xia, Long; Shen, Wenqi; Fan, Weiguo; Wang, G. Alan
• 署名单位: Elon University; Virginia Polytechnic Institute & State University; University of Iowa
• 刊物名称: JOURNAL OF MANAGEMENT INFORMATION SYSTEMS
• ISSN/ISSBN: 0742-1222
• DOI: 10.1080/07421222.2024.2340827
• 发表日期: 2024
• 页码: 453-486
• 关键词: design science research; INFORMATION; systems; REPRESENTATION; flexibility; implicit; care

摘要

Despite tremendous recent progress, extant artificial intelligence (AI) still falls short of matching human learning in effectiveness and efficiency. One fundamental disparity is that humans possess a wealth of prior knowledge, while AI lacks the essential commonsense knowledge required for learning tasks. Guided by schema theory, we employ the design science research methodology to introduce a novel knowledge-aware learning framework to harness the knowledge-based processes in human learning. Unlike existing pre-trained large language models (LLMs) and knowledge-aware approaches that treat knowledge in considerably different ways from humans, our theoretically grounded framework closely mimics how humans acquire, represent, activate, and utilize knowledge. The extensive evaluations in the context of text analytics tasks demonstrate that our design achieves comparable performance to the state-of-the-art LLMs and enhances model generalizability and learning efficiency. This study takes a step forward by bringing cognitive science into building cognitively plausible AI and human-AI collaboration research.