Summary of “my Grade Is Wrong!”: a Contestable Ai Framework For Interactive Feedback in Evaluating Student Essays, by Shengxin Hong et al.

“My Grade is Wrong!”: A Contestable AI Framework for Interactive Feedback in Evaluating Student Essays

by Shengxin Hong, Chang Cai, Sixuan Du, Haiyue Feng, Siyuan Liu, Xiuyi Fan

First submitted to arxiv on: 11 Sep 2024

GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty	Written by	Summary
High	Paper authors	High Difficulty Summary Read the original abstract here
Medium	GrooveSquid.com (original content)	Medium Difficulty Summary This paper introduces CAELF, a framework for automating interactive feedback using Large Language Models (LLMs). The authors argue that traditional one-way feedback is less effective than interactive feedback, but current LLMs struggle with reasoning and interaction. To overcome this limitation, they propose a Contestable AI Empowered LLM Framework that integrates a multi-agent system with computational argumentation. This framework allows students to query, challenge, and clarify their feedback through a Teacher Agent that aggregates evaluations from multiple Teaching-Assistant Agents (TA Agents). A case study on 500 critical thinking essays demonstrates that CAELF significantly improves interactive feedback, enhancing the reasoning and interaction capabilities of LLMs.
Low	GrooveSquid.com (original content)	Low Difficulty Summary This paper creates a special computer system to help teachers give better feedback to students. Right now, teachers often only get one chance to give feedback, but this new system lets them go back and forth with students until they understand each other. The system uses computers that are really good at understanding language, called Large Language Models (LLMs). But even these super smart computers struggle to have a conversation with people. So, the authors created a special framework that helps the LLMs work better by adding some extra helpers, like “Teacher Agents” and “Teaching-Assistant Agents.” These agents help the computer understand what’s going on and give feedback in a way that makes sense for students.