<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Education on Ye Joo Park's Blog</title><link>https://park.is/categories/education/</link><description>Recent content in Education on Ye Joo Park's Blog</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Mon, 08 Sep 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://park.is/categories/education/index.xml" rel="self" type="application/rss+xml"/><item><title>Using GPT to Generate Paper Feedback</title><link>https://park.is/notebooks/20250908_generate_paper_feedback_using_gpt/</link><pubDate>Mon, 08 Sep 2025 00:00:00 +0000</pubDate><guid>https://park.is/notebooks/20250908_generate_paper_feedback_using_gpt/</guid><description>&lt;div&#10; class="cell border-box-sizing text_cell rendered"&#10; id="cell-id=cec6d515-3cbc-4cf7-a028-dd970afe0740"&#10;&gt;&#10; &lt;div class="prompt input_prompt"&gt;&lt;/div&gt;&#10; &lt;div class="inner_cell"&gt;&#10; &lt;div class="text_cell_render border-box-sizing rendered_html"&gt;&#10; &lt;p&gt;&#10; In 2012, I graded hundreds of papers as a teaching assistant. This was a&#10; time-consuming and subjective process, and I often spent days grading&#10; just to meet deadlines.&#10; &lt;/p&gt;&#10; &lt;p&gt;&#10; Large language models (LLMs) like GPT-5 are transforming education,&#10; including the grading of written assignments. LLMs provide an efficient&#10; and scalable way to assess students' writing while also generating&#10; personalized feedback. However, my experience using LLMs for grading has&#10; been unreliable for the following reasons:&#10; &lt;/p&gt;</description></item></channel></rss>