The launch of ChatGPT in November 2022 precipitated a panic among some
educators while prompting qualified enthusiasm from others. Under the umbrella
term Generative AI, ChatGPT is an example of a range of technologies for the
delivery of computer-generated text, image, and other digitized media. This
paper examines the implications for education of one generative AI technology,
chatbots responding from large language models, or C-LLM. It reports on an
application of a C-LLM to AI review and assessment of complex student work. In
a concluding discussion, the paper explores the intrinsic limits of generative
AI, bound as it is to language corpora and their textual representation through
binary notation. Within these limits, we suggest the range of emerging and
potential applications of Generative AI in education.

本文探讨了一种生成模型技术 —— 来自大型语言模型的聊天机器人，并报告了一项将其应用于复杂学生作品的评估中的案例，然后讨论了生成 AI 的内在限制和潜在应用。

生成人工智能：对教育的影响和应用

Generative AI: Implications and Applications for Education

Student assessment is one of the most fundamental tasks in the field of AI
Education (AIEd). One of the most common approach to student assessment is
Knowledge Tracing (KT), which evaluates a student's knowledge state by
predicting whether the student will answer a given question correctly or not.
However, in the context of multiple choice (polytomous) questions, conventional
KT approaches are limited in that they only consider the binary (dichotomous)
correctness label (i.e., correct or incorrect), and disregard the specific
option chosen by the student. Meanwhile, Option Tracing (OT) attempts to model
a student by predicting which option they will choose for a given question, but
overlooks the correctness information. In this paper, we propose
Dichotomous-Polytomous Multi-Task Learning (DP-MTL), a multi-task learning
framework that combines KT and OT for more precise student assessment. In
particular, we show that the KT objective acts as a regularization term for OT
in the DP-MTL framework, and propose an appropriate architecture for applying
our method on top of existing deep learning-based KT models. We experimentally
confirm that DP-MTL significantly improves both KT and OT performances, and
also benefits downstream tasks such as Score Prediction (SP).

本文提出了一种多任务学习框架，称为 Dichotomous-Polytomous Multi-Task Learning（DP-MTL），该框架综合了知识追踪和选项追踪，以更精确地评估学生的知识状态，并证实该框架可以明显提高知识追踪和选项追踪的性能，并 profit downstream tasks such as Score Prediction（SP）。