Downloads
Download
大语言模型支持下高校英语写作形成性评价机制研究——基于教师反馈与多模型反馈的比较. (2026). 教育学刊, 4(5), 71-82. https://doi.org/10.62836/jer.v4n5.1099
Copyright (c) 2026 任晨扬, 魏宏

This work is licensed under a Creative Commons Attribution 4.0 International License.
大语言模型支持下高校英语写作形成性评价机制研究——基于教师反馈与多模型反馈的比较
任晨扬,魏宏*
温州大学教育学院,浙江温州
摘要:在高校英语写作教学中,形成性评价长期面临反馈成本高、反馈频率低与个性化支持不足等现实困境。为探讨大语言模型支持下写作形成性评价的优化路径,本文以96名高校一年级研究生为对象, 在记叙文、应用文、议论文和说明文四类写作任务中,比较教师反馈、GPT-5 Fast、GPT-5 Thinking与GPT-5 Thinking+小样本提示四种方式在反馈特征、评分一致性、反馈实施、作文进步及学习体验等方面的差异。研究发现:优化后的推理模型在具体建议、可操作反馈和评分一致性上最接近教师反馈; 四种反馈方式均能促进学生作文修订,但总体呈现“教师反馈≈GPT-5 Thinking+小样本提示>GPT-5 Thinking>GPT-5 Fast”的格局;高质量反馈还伴随写作自我效能感提升与写作焦虑下降。研究表明,大语言模型可以成为高校英语写作形成性评价的有效辅助工具,但其教学价值不取决于是否使用人工智能本身,而取决于提示设计、评价标准以及教师主导下的人机协同机制。本文据此提出“教师把关—模型细化—学生实施”的高校英语写作形成性评价优化路径。
参考文献
[1] 饶劲松,李薇,李珩.高校数字化转型策略研究[J].中国大学教学,2025,3:52-60.
[2] Black P, Wiliam D. Assessment and classroom learning[J]. Assessment in Education: principles, policy & practice, 1998, 5(1): 7-74.
[3] Hattie J, Timperley H. The power of feedback[J]. Review of educational research, 2007, 77(1): 81-112.
[4] 王海啸.生成式人工智能在大学英语教学改革中的应用探究——以“通用学术英语写作”课程教学改革实践为例[J].外语教育研究前沿,2024,7(04):41-50+95.
[5] Fu Q K, Zou D, Xie H, et al. A review of AWE feedback: Types, learning outcomes, and implications[J]. Computer Assisted Language Learning, 2024, 37(1-2): 179-221.
[6] Dai W, Lin J, Jin H, et al. Can large language models provide feedback to students? A case study on ChatGPT[C]//2023 IEEE international conference on advanced learning technologies (ICALT). IEEE, 2023: 323-325.
[7] Ding L, Zou D, Kohnke L. ChatGPT as an automated writing evaluation tool: how students perceive it and how it affects their writing[J]. Education and Information Technologies, 2025: 1-23.
[8] Shute V J. Focus on formative feedback[J]. Review of educational research, 2008, 78(1): 153-189.
[9] AlGhamdi E, Li Y, Gašević D, et al. Leveraging prompt-based LLMs for automated scoring and feedback generation in higher education[J]. Computers & Education, 2025: 105511.
[10] Yan D, Zhang S. L2 writer engagement with automated written corrective feedback provided by ChatGPT: A mixed- method multiple case study[J]. Humanities and Social Sciences Communications, 2024, 11(1): 1-14.
[11] Zhang Y, Liu Y. Designing ChatGPT-mediated feedback activities in EFL writing: a design-based study of the dialogic feedback triangle[J]. Assessment & Evaluation in Higher Education, 2026, 51(1): 137-160.
[12] Wu J, Li J, Ge Z, et al. Effectiveness of generative AI in automated written corrective feedback with prompting[J]. Journal of Educational Computing Research, 2025, 63(6): 1493-1527.
[13] 滕琳,杨玉鑫,杨静.人工智能写作反馈模式下自我调节能力对多维反馈投入的影响研究[J].外语教育研究前沿,2025,8(03):85-96.
[14] 孙培健, 许嘉宇, 张军. 生成式人工智能反馈对大学生英文作文质量的增值效益研究[J].外语教育研究前沿,2025,8(04):24-36.
[15] 蒋贵友,殷文轩.变革抑或危机:大语言模型赋能大学教学及其限度——基于斯坦福大学的案例考察[J].电化教育研究,2025,46(01):122-128.
[16] Nicol D J, Macfarlane‐Dick D. Formative assessment and self‐regulated learning: A model and seven principles of good feedback practice[J]. Studies in higher education, 2006, 31(2): 199-218.
[17] Kluger A N, DeNisi A. The effects of feedback interventions on performance: a historical review, a meta-analysis, and a preliminary feedback intervention theory[J]. Psychological bulletin, 1996, 119(2): 254.
[18] Carless D, Boud D. The development of student feedback literacy: Enabling uptake of feedback[J]. Assessment & evaluation in higher education, 2018, 43(8): 1315-1325.
[19] Lu Q, Yao Y, Xiao L, et al. Can ChatGPT effectively complement teacher assessment of undergraduate students’ academic writing?[J]. Assessment & Evaluation in Higher Education, 2024, 49(5): 616-633.
[20] Teimouri Y, Goetze J, Plonsky L. Second language anxiety and achievement: A meta-analysis[J]. Studies in second language acquisition, 2019, 41(2): 363-387.
[21] 杨现民,曾佳尧,李新.人工智能与教育深度融合的场景细化及落地实践[J].开放教育研究,2025,31(1):82-92.
[22] 李焕宏,薛澜.生成式人工智能应用的使能型风险规制——以高等教育应用为例[J].清华大学教育研究,2025,46(01):68-78.DOI:10.14138/j.1001-4519.2025.01.006811.
[23] Zhang Z V, Hyland K. Student engagement with teacher and automated feedback on L2 writing[J]. Assessing Writing, 2018, 36: 90-102.
[24] Lee S, Choe H, Zou D, et al. Generative AI (GenAI) in the language classroom: A systematic review[J]. Interactive Learning Environments, 2026, 34(1): 335-359.
[25] Zhang Z, Aubrey S, Huang X, et al. The role of generative AI and hybrid feedback in improving L2 writing skills: A comparative study[J]. Innovation in Language Learning and Teaching, 2025: 1-19.
[26] 宋宇,焦丽珍,林如.创新人才培养导向下的课堂教学智能评价研究[J].全球教育展望,2025,54(03):119-134.
[27] 罗杨洋,周国辉,韩锡斌.高校数字化转型如何适配有效策略?——基于技术、组织、环境协同的视角[J].现代教育技术,2025,35(06):46-55.
[28] 张卓,陈晨.高等教育数字治理的“悬浮化”:表征、机理及矫治[J].西南大学学报(社会科学版),2025,51(03):240-252+334-335.
[29] 宋宇,许昌良,穆欣欣.生成式人工智能赋能的新型课堂教学评价与优化研究[J].现代教育技术,2024,34(12):27-36.
[30] Cheng Y S. A measure of second language writing anxiety: Scale development and preliminary validation[J]. Journal of second language writing, 2004, 13(4): 313-335.
[31] 李航.大学生英语写作自我效能感量表的编制[J].北京第二外国语学院学报,2014,36(12):70-76.
[2] Black P, Wiliam D. Assessment and classroom learning[J]. Assessment in Education: principles, policy & practice, 1998, 5(1): 7-74.
[3] Hattie J, Timperley H. The power of feedback[J]. Review of educational research, 2007, 77(1): 81-112.
[4] 王海啸.生成式人工智能在大学英语教学改革中的应用探究——以“通用学术英语写作”课程教学改革实践为例[J].外语教育研究前沿,2024,7(04):41-50+95.
[5] Fu Q K, Zou D, Xie H, et al. A review of AWE feedback: Types, learning outcomes, and implications[J]. Computer Assisted Language Learning, 2024, 37(1-2): 179-221.
[6] Dai W, Lin J, Jin H, et al. Can large language models provide feedback to students? A case study on ChatGPT[C]//2023 IEEE international conference on advanced learning technologies (ICALT). IEEE, 2023: 323-325.
[7] Ding L, Zou D, Kohnke L. ChatGPT as an automated writing evaluation tool: how students perceive it and how it affects their writing[J]. Education and Information Technologies, 2025: 1-23.
[8] Shute V J. Focus on formative feedback[J]. Review of educational research, 2008, 78(1): 153-189.
[9] AlGhamdi E, Li Y, Gašević D, et al. Leveraging prompt-based LLMs for automated scoring and feedback generation in higher education[J]. Computers & Education, 2025: 105511.
[10] Yan D, Zhang S. L2 writer engagement with automated written corrective feedback provided by ChatGPT: A mixed- method multiple case study[J]. Humanities and Social Sciences Communications, 2024, 11(1): 1-14.
[11] Zhang Y, Liu Y. Designing ChatGPT-mediated feedback activities in EFL writing: a design-based study of the dialogic feedback triangle[J]. Assessment & Evaluation in Higher Education, 2026, 51(1): 137-160.
[12] Wu J, Li J, Ge Z, et al. Effectiveness of generative AI in automated written corrective feedback with prompting[J]. Journal of Educational Computing Research, 2025, 63(6): 1493-1527.
[13] 滕琳,杨玉鑫,杨静.人工智能写作反馈模式下自我调节能力对多维反馈投入的影响研究[J].外语教育研究前沿,2025,8(03):85-96.
[14] 孙培健, 许嘉宇, 张军. 生成式人工智能反馈对大学生英文作文质量的增值效益研究[J].外语教育研究前沿,2025,8(04):24-36.
[15] 蒋贵友,殷文轩.变革抑或危机:大语言模型赋能大学教学及其限度——基于斯坦福大学的案例考察[J].电化教育研究,2025,46(01):122-128.
[16] Nicol D J, Macfarlane‐Dick D. Formative assessment and self‐regulated learning: A model and seven principles of good feedback practice[J]. Studies in higher education, 2006, 31(2): 199-218.
[17] Kluger A N, DeNisi A. The effects of feedback interventions on performance: a historical review, a meta-analysis, and a preliminary feedback intervention theory[J]. Psychological bulletin, 1996, 119(2): 254.
[18] Carless D, Boud D. The development of student feedback literacy: Enabling uptake of feedback[J]. Assessment & evaluation in higher education, 2018, 43(8): 1315-1325.
[19] Lu Q, Yao Y, Xiao L, et al. Can ChatGPT effectively complement teacher assessment of undergraduate students’ academic writing?[J]. Assessment & Evaluation in Higher Education, 2024, 49(5): 616-633.
[20] Teimouri Y, Goetze J, Plonsky L. Second language anxiety and achievement: A meta-analysis[J]. Studies in second language acquisition, 2019, 41(2): 363-387.
[21] 杨现民,曾佳尧,李新.人工智能与教育深度融合的场景细化及落地实践[J].开放教育研究,2025,31(1):82-92.
[22] 李焕宏,薛澜.生成式人工智能应用的使能型风险规制——以高等教育应用为例[J].清华大学教育研究,2025,46(01):68-78.DOI:10.14138/j.1001-4519.2025.01.006811.
[23] Zhang Z V, Hyland K. Student engagement with teacher and automated feedback on L2 writing[J]. Assessing Writing, 2018, 36: 90-102.
[24] Lee S, Choe H, Zou D, et al. Generative AI (GenAI) in the language classroom: A systematic review[J]. Interactive Learning Environments, 2026, 34(1): 335-359.
[25] Zhang Z, Aubrey S, Huang X, et al. The role of generative AI and hybrid feedback in improving L2 writing skills: A comparative study[J]. Innovation in Language Learning and Teaching, 2025: 1-19.
[26] 宋宇,焦丽珍,林如.创新人才培养导向下的课堂教学智能评价研究[J].全球教育展望,2025,54(03):119-134.
[27] 罗杨洋,周国辉,韩锡斌.高校数字化转型如何适配有效策略?——基于技术、组织、环境协同的视角[J].现代教育技术,2025,35(06):46-55.
[28] 张卓,陈晨.高等教育数字治理的“悬浮化”:表征、机理及矫治[J].西南大学学报(社会科学版),2025,51(03):240-252+334-335.
[29] 宋宇,许昌良,穆欣欣.生成式人工智能赋能的新型课堂教学评价与优化研究[J].现代教育技术,2024,34(12):27-36.
[30] Cheng Y S. A measure of second language writing anxiety: Scale development and preliminary validation[J]. Journal of second language writing, 2004, 13(4): 313-335.
[31] 李航.大学生英语写作自我效能感量表的编制[J].北京第二外国语学院学报,2014,36(12):70-76.


