Onboard model, capable of providing estimated measurable values and unmeasurable performance parameters of interest with the maximal fidelity, serves as the cornerstone for aircraft engine control and fault diagnosis. As aircraft engine configurations grow increasingly complex to meet the performance specifications of next-generation propulsion systems, significant challenges is proposed to the accuracy and real-time performance of onboard models. Consequently, the development of onboard modeling techniques has become increasingly crucial.

With the development of the Internet and intelligent education systems, the significance of cognitive diagnosis has become increasingly acknowledged. Cognitive diagnosis models (CDMs) aim to characterize learners’ cognitive states based on their responses to a series of exercises. However, conventional CDMs often struggle with less frequently observed learners and items, primarily due to limited prior knowledge. Recent advancements in large language models (LLMs) offer a promising avenue for infusing rich domain information into CDMs. However, integrating LLMs directly into CDMs poses significant challenges. While LLMs excel in semantic comprehension, they are less adept at capturing the fine-grained and interactive behaviours central to cognitive diagnosis. Moreover, the inherent difference between LLMs’ semantic representations and CDMs’ behavioural feature spaces hinders their seamless integration. To address these issues, this research proposes a model-agnostic framework to enhance the knowledge of CDMs through LLMs extensive knowledge. It enhances various CDM architectures by leveraging LLM-derived domain knowledge and the structure of observed learning outcomes taxonomy. It operates in two stages: first, LLM diagnosis, which simultaneously assesses learners via educational techniques to establish a richer and a more comprehensive knowledge representation; second, cognitive level alignment, which reconciles the LLM’s semantic space with the CDM’s behavioural domain through contrastive learning and mask-reconstruction learning. Empirical evaluations on multiple real-world datasets demonstrate that the proposed framework significantly improves diagnostic accuracy and underscoring the value of integrating LLM-driven semantic knowledge into traditional cognitive diagnosis paradigms. 

A strong geomagnetic storm in spring 2024 brought the northern lights unusually far south, as the auroral oval expanded well beyond its typical position. "I am surprised at how sparse the measurement network is, even though we know that the impacts of space weather can vary greatly from one area to another," says Doctoral Researcher Otto Kärhä from the University of Oulu, Finland.