WrAFT (Writing Assessment and Feedback Tool)¶
Product or Programme · All products and programmes
Evidence · 5 claims (4 for, 1 mixed) · 2 studies (2 design),q2· 0 of 2 report an effect size · 5 claims rest on one study
Description¶
WrAFT is a deployable, modular LLM-powered automated writing evaluation and feedback system developed by Adnan Labib and colleagues for argumentative-essay writers.
Components¶
- WrAFT: deployable modular AWE system with interactive UI for in-line corrective edits and anchored comments: WrAFT (Writing Assessment and Feedback Tool) is a modular LLM-powered automated writing evaluation system for argumentative essays, combining a fine-tuned GPT-4o scoring module, a GPT-4o surface-level feedback module, and Claude 3.7 macro and micro deep-level feedback pipelines. Its interactive UI shows a predicted score, a surface-level tab with three display modes including track-changes, and a deep-level tab modeled after Microsoft Word's Comment feature with color-coded highlights. The article states "An interactive user interface has been developed for the system, publicly available and free to use", with a deployable code package on GitHub and a web application at wraft.net. (Adnan Labib et al. (2026))
Claims¶
- Fine-tuned GPT-4o achieves state-of-the-art scoring of TOEFL argumentative essays with QWK 0.84 and RMSE 0.44 against official scores [+M]
- Directly prompted GPT-4o surface-level corrective edits were judged necessary and effective in 96.14% of 2049 identified edits [+M]
- Directly prompted Claude 3.7 macro-level deep feedback was judged effective for 93.03% of 201 paragraph-level comments [+M]
- Directly prompted Claude 3.7 micro-level deep feedback was judged both necessary and effective in 94.69% of 630 comments [+M]
- Prompt-based scoring prompts developed on one year's test generalize to the next year's edition with only minor adjustments [~W]
Related Products and Programmes¶
Key Sources¶
- Adnan Labib, Yixuan Huang, Jiahui Wu, John Maurice Gayed, Zheng Yuan, Qiao Wang. (2026). WrAFT: a Modularized Automated Writing Evaluation System for Argumentative Essays. arXiv preprint. https://arxiv.org/abs/2607.14524
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
wraft-writing-assessment-and-feedback-tool |
title |
WrAFT (Writing Assessment and Feedback Tool) |
description |
WrAFT is a deployable, modular LLM-powered automated writing evaluation and feedback system developed by Adnan Labib and colleagues for argumentative-essay writers. |
status |
review |
product_kind |
software |
generated |
by process:settle-candidates on 2026-10-12 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.