# AI-Mediated Feedback Improves Student Revisions: A Randomized Trial with FeedbackWriter in a Large Undergraduate Course

arXiv: https://arxiv.org/abs/2602.16820 · HTML: https://mlsanity.com/paper/2602.16820/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 132 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems](https://mlsanity.com/paper/2305.14536/) (2023)
- [Fine-tuning ChatGPT for Automatic Scoring](https://mlsanity.com/paper/2310.10072/) (2023)
- [Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise](https://mlsanity.com/paper/2410.03017/) (2024)
- [Learning gain differences between ChatGPT and human tutor generated algebra hints](https://mlsanity.com/paper/2302.06871/) (2023)
- [How Knowledge Workers Think Generative AI Will (Not) Transform Their Industries](https://mlsanity.com/paper/2310.06778/) (2023)
- [A large language model-assisted education tool to provide feedback on open-ended responses](https://mlsanity.com/paper/2308.02439/) (2023)
- [Can We Trust AI-Generated Educational Content? Comparative Analysis of Human and AI-Generated Learning Resources](https://mlsanity.com/paper/2306.10509/) (2023)
- [TutorGym: A Testbed for Evaluating AI Agents as Tutors and Students](https://mlsanity.com/paper/2505.01563/) (2025)
- [Using Large Language Models to Assess Tutors' Performance in Reacting to Students Making Math Errors](https://mlsanity.com/paper/2401.03238/) (2024)
- [Improving Student Learning with Hybrid Human-AI Tutoring: A Three-Study Quasi-Experimental Investigation](https://mlsanity.com/paper/2312.11274/) (2023)
- [Do LLMs Make Mistakes Like Students? Exploring Natural Alignment between Language Models and Human Error Patterns](https://mlsanity.com/paper/2502.15140/) (2025)
- [Towards Adaptive Feedback with AI: Comparing the Feedback Quality of LLMs and Teachers on Experimentation Protocols](https://mlsanity.com/paper/2502.12842/) (2025)
- [From First Draft to Final Insight: A Multi-Agent Approach for Feedback Generation](https://mlsanity.com/paper/2505.04869/) (2025)
- [SPARK: Real-Time Monitoring of Multi-Faceted Programming Exercises](https://mlsanity.com/paper/2601.22256/) (2026)
- [LLM-Generated Feedback Supports Learning If Learners Choose to Use It](https://mlsanity.com/paper/2506.17006/) (2025)
- [Assessing Large Language Models for Automated Feedback Generation in Learning Programming Problem Solving](https://mlsanity.com/paper/2503.14630/) (2025)
- [Exploring LLM-Generated Feedback for Economics Essays: How Teaching Assistants Evaluate and Envision Its Use](https://mlsanity.com/paper/2505.15596/) (2025)

## Built on by (most cited first, 1 of 1)

- [FOXGLOVE: Understanding Goal-Oriented and Anchored Writing Feedback from Experts and LLMs on Argumentative Essays](https://mlsanity.com/paper/2606.06271/) (2026)

## 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.