Predicting the Quality of Revisions in Argumentative Writing

Zhexiong Liu, Diane Litman, Elaine Wang, Lindsay Matsumura, Richard Correnti
6/1/2023
cs.CLcs.AI

No official code found. Best implementation: ZhexiongLiu/Revision-Quality-Prediction (4 stars, MIT, last commit 2023-08-01).

Abstract

The ability to revise in response to feedback is critical to students' writing success. In the case of argument writing in specific, identifying whether an argument revision (AR) is successful or not is a complex problem because AR quality is dependent on the overall content of an argument. For example, adding the same evidence sentence could strengthen or weaken existing claims in different argument contexts (ACs). To address this issue we developed Chain-of-Thought prompts to facilitate ChatGPT-generated ACs for AR quality predictions. The experiments on two corpora, our annotated elementary essays and existing college essays benchmark, demonstrate the superiority of the proposed ACs over baselines.

View on arXivView PDF

Code Implementations(1)

ZhexiongLiu/Revision-Quality-PredictionCommunity100%
MIT

Paper: Predicting the Quality of Revisions in Argumentative Writing.

41PythonMay 26, 20233 years agoMIT
argument-contextessaysrevisions

Similar Papers

Predicting Desirable Revisions of Evidence and Reasoning in Argumentative Writing

89% match2023

To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support

85% match2023

ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation

81% match2026

Writing for the Reviewer: Defensive Writing in GPT Models

80% match2026

eRevise+RF: A Writing Evaluation System for Assessing Student Essay Revisions and Providing Formative Feedback

80% match1 repo22025

Evaluation of ChatGPT Feedback on ELL Writers' Coherence and Cohesion

79% match2023

Cite this paper

@article{liu2023predicting,
  title  = {Predicting the Quality of Revisions in Argumentative Writing},
  author = {Zhexiong Liu and Diane Litman and Elaine Wang and Lindsay Matsumura and Richard Correnti},
  year   = {2023},
  eprint = {2306.00667},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.00667v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.00667.svg)](https://codeofpaper.com/paper/2306.00667)

Discussion