AI-Mediated Feedback Improves Student Revisions: A Randomized Trial with FeedbackWriter in a Large Undergraduate Course
Not on the map. Why?
Abstract (arXiv)
Despite growing interest in using LLMs to generate feedback on students' writing, little is known about how students respond to AI-mediated versus human-provided feedback. We address this gap through a randomized controlled trial in a large introductory economics course (N=354), where we introduce and deploy FeedbackWriter - a system that generates AI suggestions to teaching assistants (TAs) while they provide feedback on students' knowledge-intensive essays. TAs have the full capacity to adopt, edit, or dismiss the suggestions. Students were randomly assigned to receive either handwritten feedback from TAs (baseline) or AI-mediated feedback where TAs received suggestions from FeedbackWriter. Students revise their drafts based on the feedback, which is further graded. In total, 1,366 essays were graded using the system. We found that students receiving AI-mediated feedback produced significantly higher-quality revisions, with gains increasing as TAs adopted more AI suggestions. TAs found the AI suggestions useful for spotting gaps and clarifying rubrics.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 132 references that are in the map. First posted on arXiv 18 Feb 2026.
Builds on
22 of 132 references.
References · 22
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
- 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 651
- 2018Manipulating and Measuring Model Interpretabilitycited by 256
- 2023MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problemscited by 128
- 2023Fine-tuning ChatGPT for Automatic Scoringcited by 50
- 2024Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertisecited by 46
- 2023Learning gain differences between ChatGPT and human tutor generated algebra hintscited by 42
- 2023How Knowledge Workers Think Generative AI Will (Not) Transform Their Industriescited by 29
- 2023A large language model-assisted education tool to provide feedback on open-ended responsescited by 21
- 2023Can We Trust AI-Generated Educational Content? Comparative Analysis of Human and AI-Generated Learning Resourcescited by 12
10 more
- 2025TutorGym: A Testbed for Evaluating AI Agents as Tutors and Studentscited by 10
- 2024Using Large Language Models to Assess Tutors' Performance in Reacting to Students Making Math Errorscited by 9
- 2023Improving Student Learning with Hybrid Human-AI Tutoring: A Three-Study Quasi-Experimental Investigationcited by 8
- 2025Do LLMs Make Mistakes Like Students? Exploring Natural Alignment between Language Models and Human Error Patternscited by 8
- 2025Towards Adaptive Feedback with AI: Comparing the Feedback Quality of LLMs and Teachers on Experimentation Protocolscited by 6
- 2025From First Draft to Final Insight: A Multi-Agent Approach for Feedback Generationcited by 5
- 2026SPARK: Real-Time Monitoring of Multi-Faceted Programming Exercisescited by 5
- 2025LLM-Generated Feedback Supports Learning If Learners Choose to Use Itcited by 4
- 2025Assessing Large Language Models for Automated Feedback Generation in Learning Programming Problem Solvingcited by 2
- 2025Exploring LLM-Generated Feedback for Economics Essays: How Teaching Assistants Evaluate and Envision Its Usecited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.