Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions

TL;DR

This paper introduces PROF, a method that uses language model simulated student revisions to generate more effective writing feedback, significantly improving student revision quality in an economic essay task.

Contribution

PROF is a novel approach that iteratively optimizes feedback generation by learning from simulated student revisions, enhancing writing improvement beyond baseline methods.

Findings

PROF outperforms baseline feedback methods in improving student revisions.

The approach demonstrates increased pedagogical value without explicit training for that aspect.

Effective feedback generation correlates with improved student revision quality.

Abstract

Providing feedback is widely recognized as crucial for refining students' writing skills. Recent advances in language models (LMs) have made it possible to automatically generate feedback that is actionable and well-aligned with human-specified attributes. However, it remains unclear whether the feedback generated by these models is truly effective in enhancing the quality of student revisions. Moreover, prompting LMs with a precise set of instructions to generate feedback is nontrivial due to the lack of consensus regarding the specific attributes that can lead to improved revising performance. To address these challenges, we propose PROF that PROduces Feedback via learning from LM simulated student revisions. PROF aims to iteratively optimize the feedback generator by directly maximizing the effectiveness of students' overall revising performance as simulated by LMs. Focusing on an economic essay assignment, we empirically test the efficacy of PROF and observe that our approach not only surpasses a variety of baseline methods in effectiveness of improving students' writing but also demonstrates enhanced pedagogical values, even though it was not explicitly trained for this aspect.