The COM Essay Assessor

When AI-Mediated Feedback Writing Works and When It Does Not: Lessons Learned from Two Classroom Cases

Student Evaluation of Repeated AI Feedback Across a Semester of Writing

Analysis of reflective essay-feedback-appraisal instances from 283 Estonian bachelor students across one semester contributes descriptive classroom evidence on integration of AI feedback - a fast and scalable way to provide immediate writing advice, but not a self-contained route to better reflection.

How Well Does AI-Generated Feedback Work? Intrinsic and Extrinsic Evaluation across more than 20,000 EFL Essay Drafts

This study examines feedback in English as a Foreign Language (EFL) writing contexts, focusing on written corrective feedback (WCF). Large language models (LLMs) can provide WCF at scale, but aligning them with pedagogical best practices remains an ongoing challenge. WCF meeting criteria like factuality or relevance may still be unsuitable for learning contexts, highlighting the need for extrinsic evaluation based on the learner's perspective. We deployed WCF systems in a university-level EFL class with nearly 2,000 students, collecting over 20,000 drafts. We evaluated the generated WCF from two perspectives: intrinsic evaluation by experienced English teachers using a rubric, and extrinsic evaluation via student feedback and engagement metrics. Results revealed low alignment between teacher expert ratings and student feedback. These findings suggest that traditional expert evaluation alone may not fully capture WCF's usability or helpfulness from the learner's perspective, highlighting the importance of learner-centered evaluation frameworks for AI-based applications in language education.

Affordances and Constraints of AI-Generated Writing Feedback

The findings suggest that AI-generated feedback supported targeted revision when it is accessible, interpretable, and aligned with classroom assessment criteria.

A rubric to assess generative AI-based feedback on student writing assignments

ABSTRACT Generative artificial intelligence (GenAI) tools are an increasingly common resource used in the classroom and writing process. The landscape of available GenAI tools is rapidly evolving, so having a systematic and straightforward way to evaluate new tools for incorporation into the classroom is key. For example, in science writing education, GenAI tools can be used as a supplement to instructor feedback on student writing, allowing an additional opportunity for critique and revision by the student. Here, we describe a rubric we developed to enable instructors to assess differences between feedback provided by GenAI models based on five key areas: (i) accuracy, (ii) constructiveness, (iii) clarity and readability, (iv) recognition of strengths, and (v) original text. We show data comparing the feedback provided by multiple GenAI models on student work based on course guidelines. This rubric can serve as a resource for other instructors interested in evaluating various GenAI models for use as scientific writing feedback supplements in their own classrooms.

A Mobile System for Formative Assessment and Teacher-Reviewed Feedback

Within the limits of this small-scale classroom evaluation, the findings suggest that rubric-guided LLM scoring may support formative assessment in mobile classrooms, provided teacher oversight is maintained for borderline cases.