基于生成式AI的自适应写作反馈和任务学习系统理论探究

doi:10.3969/j.issn.1674-8921.2025.05.014

摘要/Abstract

摘要：

生成式AI在教育领域的影响日益深远,但现有研究多聚焦于技术层面和实际应用,缺乏对其理论基础的深入探讨。为推动生成式AI在智能系统开发中的理论建设,本研究采用文献综述与理论分析方法,基于语言学、认知心理学及教育学的跨学科视角,系统探讨了基于生成式AI的AWESOM自适应写作反馈与任务学习系统的理论框架。研究指出,语言学理论(如分布式语义学和构式语法)为系统提供了精准的语义与句法分析工具,从而生成更有效的写作反馈和任务建议;认知心理学理论(如认知负荷理论)指导信息呈现与任务设计,旨在减轻学习者的认知负担并优化其知识结构;教育学理论(如最近发展区理论)为动态调整学习任务和反馈提供理论支持,促进个性化学习体验及持续改进。各理论间的协同作用为系统设计奠定坚实基础,提升了其智能化水平与教育效能。该研究为AI赋能教育从单一技术应用走向以跨学科理论为核心的智能体建构提供了新思路。

关键词: 生成式AI, 跨学科视角, 理论探究, AWESOM系统

Abstract:

The impact of generative AI on the field of education is becoming increasingly significant. However, existing research primarily focuses on technical and practical applications, often lacking a thorough analysis of theoretical foundation. To advance the theoretical development of generative AI in artificial intelligence system design, this study employs a literature review and theoretical analysis from the cross disciplinary perspectives of linguistics, cognitive psychology, and education to explore the design principles of generative AI-based writing feedback and adaptive learning system. The findings suggest that the linguistic theories, including Distributional Semantics and Construction Grammar, provide essential semantic and grammatical analysis tools, enabling AI systems to generate more precise writing feedback and task recommendations. Cognitive Load Theory, a cognitive psychology theory, informs system design by guiding information presentation and task structuring to reduce learners’ cognitive load and optimize knowledge acquisition. The educational theory of the Zone of Proximal Development offers a framework for dynamically adjusting learning tasks and feedback, thereby supporting personalized learning experiences and continuous improvement. These theoretical foundations collectively contribute to the intelligent design of the generative AI-based adaptive writing feedback and task learning system, and their interconnections significantly enhance system adaptability and efficiency. The study offers a new perspective for advancing AI-empowered education from a focus on merely technological applications to the construction of intelligent systems grounded in interdisciplinary theories.

Key words: Generative AI, cross disciplinary perspectives, theoretical exploration, AWESOM system

中图分类号:

H319

张荔. 基于生成式AI的自适应写作反馈和任务学习系统理论探究[J]. 当代外语研究, 2025, 25(5): 132-142.

ZHANG Li. Theoretical Exploration of the Generative AI-Based Adaptive Writing Feedback and Task Learning System[J]. Contemporary Foreign Languages Studies, 2025, 25(5): 132-142.

图/表 1

参考文献 31

[1]	Azevedo, R. & A. F. Hadwin. 2005. Scaffolding self-regulated learning and metacognition-Implications for the design of computer-based scaffolds[J]. Instructional Science 33(5): 367-379.
[2]	Boas, H. C. 2010. The syntax-lexicon continuum in construction grammar: A case study of English communication verbs[J]. Belgian Journal of Linguistics 24(1): 54-82.
[3]	Brown, T. B., B. Mann, N. Ryder, et al. 2020. Language models are few-shot learners[J]. Advances in Neural Information Processing Systems 33: 1877-1901.
[4]	Bybee, J. 2010. Language, Usage and Cognition[M]. Cambridge: Cambridge University Press.
[5]	Chaiklin, S. 2003. The zone of proximal development in Vygotsky’s analysis of learning and instruction[A]. In A. Kozulin, et al. (eds.). Vygotsky’s Educational Theory in Cultural Context[C]. Cambridge: Cambridge University Press. 39-64.
[6]	Croft, W. 2001. Radical Construction Grammar: Syntactic Theory in Typological Perspective[M]. Oxford: Oxford University Press.
[7]	du Plooy, E., D. Casteleijn & D. Franzsen. 2024. Personalized adaptive learning in higher education: A scoping review of key characteristics and impact on academic performance and engagement[J]. Heliyon 10(21): e39630.
[8]	Fadieieva, L. O. 2023. Adaptive learning: A cluster-based literature review (2011-2022)[J]. Educational Technology Quarterly (3): 319-366.
[9]	Fillmore, C. J. 1988. The mechanisms of construction grammar[A]. In S. Axmaker, A. Jaisser & H. Singmaster(eds.). Proceedings of the 14th Annual Meeting of the Berkeley Linguistics Society[C]. Berkeley Berkeley Linguistics Society. 35-55.
[10]	Firth, J. R. 1957. A synopsis of linguistic theory 1930-1955[A]. In J. R. Firth (ed.) Studies in Linguistic Analysis: Special Volume of the Philological Society [C]. Oxford: Blackwell. 10-32.
[11]	Gligorea, I., M. Cioca, R. Oancea, et al. 2023. Adaptive learning using artificial intelligence in e-learning: A literature review[J]. Education Sciences 13(12): 1216.
[12]	Goldberg, A. E. 1995. Constructions: A Construction Grammar Approach to Argument Structure[M]. Chicago: University of Chicago Press.
[13]	Goldberg, A. E. 2006. Constructions at Work: The Nature of Generalization in Language[M]. Oxford: Oxford University Press.
[14]	Harris, Z. S. 1954. Distributional structure[J]. Word 10 (2-3):146-162.
[15]	Ouyang, L., J. Wu, X. Jiang, et al. 2022. Training language models to follow instructions with human feedback[J]. Advances in Neural Information Processing Systems (NeurIPS) 35: 27730-27744.
[16]	Pea, R. D. 2004. The social and technological dimensions of scaffolding and related theoretical concepts for learning, education, and human activity[J]. Journal of the Learning Sciences 13(3): 423-451.
[17]	Pollock, E., P. Chandler & J. Sweller. 2002. Assimilating complex information[J]. Learning and Instruction 12(1): 61-86.
[18]	Radford, A., J. Wu, R. Child, et al. 2019. Language models are unsupervised multitask learners[J]. OpenAI Technical Report blog 1(8):9.
[19]	Salton, G., A. Wong & C. S. Yang. 1975. A vector space model for automatic indexing[J]. Communications of the ACM 18(11): 613-620.
[20]	Shi, H. & V. Aryadoust. 2024. A systematic review of AI-based automated written feedback research[J]. ReCALL 36(2): 187-209.
[21]	Sweller, J. 1988. Cognitive load during problem solving: Effects on learning[J]. Cognitive Science 12(2): 257-285.
[22]	Sweller, J. 2010. Element interactivity and intrinsic, extraneous and germane cognitive load[J]. Educational Psychology Review 22: 123-138.
[23]	Tomasello, M. 2003. Constructing a Language: A Usage-based Theory of Language Acquisition[M]. Cambridge, MA: Harvard University Press.
[24]	Vaccaro, M., A. Almaatouq & T. Malone. 2024. When combinations of humans and AI are useful: A systematic review and meta-analysis[J]. Nature Human Behaviour 8(12): 2293-2303.
[25]	Van de Pol, J., M. Volman & J. Beishuizen. 2012. Promoting teacher scaffolding in small-group work: A contingency perspective[J]. Teaching and Teacher Education 28(2): 193-205.
[26]	Vygotsky, L. S. 1978. Mind in Society: The Development of Higher Psychological Processes[M]. Cambridge: Harvard University Press.
[27]	Zheng, X. & J. Zhang. 2025. The usage of a transformer based and artificial intelligence driven multidimensional feedback system in English writing instruction[J]. Scientific Reports 15(1): 19268.
[28]	冯志伟、张灯柯. 2024a. 语言模型与人工智能[J]. 外语研究(1): 1-19.
[29]	冯志伟、张灯柯. 2024b. 人工智能中的大语言模型[J]. 外国语文(3): 1-29.
[30]	施春宏、蔡淑美. 2022. 构式语法研究的理论问题论析[J]. 外语教学与研究(5): 643-655.
[31]	张荔、 Mark Warschauer、盛越. 2016. 自动写作评阅反馈系统研究述评与展望[J]. 当代外语研究(6): 54-61.