← 返回研究新闻
写作教师与两名大学生在研讨桌旁对照带批注的段落修改稿,简洁的视觉连线呈现不同阶段的修改重点。
会议论文会议论文20262026年10月23日· 3 min

会议论文:FeedType 检验 AI 写作反馈能否随修改过程调整重点

Norah Almousa, Shayan Peyghambari Oskoui, Raquel Coelho, Gayle Rogers, Xiang Lorraine Li, Diane Litman

Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers

500 字摘要

写作教师与两名大学生在研讨桌旁对照带批注的段落修改稿,简洁的视觉连线呈现不同阶段的修改重点。

Norah Almousa 及其同事在 10 月 5–7 日举行的 AIME-Con 会议论文集中发表 FeedType。基准使用三门大学写作课程的 1,966 个段落,在三种提示策略下比较教师反馈和六种语言模型,并以七类内容描述反馈重点。自动标注经过人工判断核对。模型虽然覆盖了大多数类别,却没有完全再现教师的适应性模式。修改阶段与表现水平的分析仅限写作课程中的 composition 课程。论文考察反馈行为,没有检验干预对学习的影响。

这项研究提供了一种提问方式:评语针对什么问题,其重点是否会适当改变?即使另一种回应更有用,系统也可能反复要求学生补充细节。即使模型的类别分布与教师接近,也不能单凭这一点证明每条评语准确或有帮助。课程、标注选择和受测模型版本,同样限制了结论适用的范围。

对 AIEDHK 读者而言,可考虑围绕同一段落的两版草稿开展写作工作坊。阅读生成反馈前,教师先判断当前作业阶段最重要的下一步。学生随后比较建议,找出每条建议针对的文字证据,并解释为什么某个问题应优先修改。这是本站提出的教学设计,并非基准研究已经评估的活动。

例如,关于本地环境议题的初稿可能需要更清楚的主张和适当来源;后续稿件也许已解决这项问题,转而需要精确说明一项限制条件。两次都要求“增加细节”,就可能遗漏不同阶段的修改重点。学生可解释为什么一条表面有用的建议会分散当前任务的注意力,让教师看到其写作判断。

本地试点可保留草稿、建议、学生选择的行动及简短理由。教师抽查有分歧和无分歧的案例,而不应假定接受更多建议就代表学习更好。审阅也应包含类别判断正确、但修改方案不适当的评语。目标是了解反馈如何支持写作过程中特定时刻的决策。

双语写作课还可检查评语是否在跨语言表达时保留作者原意。学生可依据作业目的解释修改,教师则考察语言润色是否掩盖了尚未解决的论证或缺乏依据的主张。

产品团队可在发布前明确一个评估问题:反馈是否回应了作业、当前草稿和学生表现出的困难?这能指导范围明确的审阅样本,又不必把教师过去的做法当作不可质疑的标准。之后减少辅助的独立写作可提供补充学习证据。FeedType 是检查反馈适应性的研究资源;课堂或机构采用系统,仍需了解学生实际收到的评语质量及其后果。

相关论文

Illustrative research-review scene with two raters comparing repeated and progressive activity sequences beside a screen with one rising and one falling chart.
工具 / 数据集2026
工具 / 数据集 239

Preprint: Raising a tutor metric lowered human ratings in an optimization experiment

Daniel Domínguez Figaredo, Rafael Fernández De la Cruz

arXiv preprint

An optimization experiment produced higher automated scores but lower human ratings for instructional sequences. Its synthetic cases and constrained intervention make it a warning about evaluation design, not evidence of harm to actual students.

preprintAI tutoringevaluation validity
阅读 500 字摘要 →
A South Asian female lecturer and a White male university student examine two differently annotated statistics feedback sheets beside a hand-drawn confidence-interval diagram
期刊论文2026
期刊论文 216

Students’ feedback ratings reflected source credibility without consistently matching expert judgments

Tanya Nazaretsky, Hagit Gabbay, Tanja Käser

Computers and Education: Artificial Intelligence

Researchers compared human and AI feedback on 979 responses from six university STEM courses, then examined ratings from 472 students. Expert analysis found broadly similar pedagogical quality, while students’ judgments were associated with their views of the source’s credibility. The study did not measure feedback uptake or learning gains. For educators, it raises a practical question: how can students justify an evaluation of advice before deciding whether to use it?

feedback literacysource credibilityhigher education
阅读 500 字摘要 →
A mathematics lecturer and peer discuss a university student's induction proof beside a laptop showing feedback on the next step.
会议论文2026
会议论文 206

LeanTutor: Towards a Verified AI Mathematical Proof Tutor

Manooshree Patel, Rayna Bhattacharyya, Thomas Lu, Arnav Mehta, Niels Voss, Narges Norouzi, Gireeja Ranade

Proceedings of the AAAI Conference on Artificial Intelligence

LeanTutor connects a language model to the Lean theorem prover to support mathematical proof feedback. Its technical evaluation shows promising hints on a small selected benchmark, but also exposes a crucial boundary: a verifier can check the formal proof only after the learner's words have been translated correctly. The study did not test classroom learning, and feedback evaluation excluded failed translations. It is an early system design with explicit limitations, not a validated replacement for mathematics instruction.

Mathematics EducationIntelligent TutoringFormal Verification
阅读 500 字摘要 →