Summary of Grading Massive Open Online Courses Using Large Language Models, by Shahriar Golchin et al.
Grading Massive Open Online Courses Using Large Language Models
by Shahriar Golchin, Nikhil Garuda, Christopher Impey, Matthew Wenger
First submitted to arxiv on: 16 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 The study explores the feasibility of using large language models (LLMs) to replace peer grading in massive open online courses (MOOCs). The authors adapt a zero-shot chain-of-thought (ZCoT) prompting technique to automate feedback, testing three distinct prompts on two LLMs across three MOOCs. Results show that ZCoT with instructor-provided correct answers and rubrics produces grades more aligned with instructor assignments compared to peer grading. This has promising implications for improving the learning experience for millions of online learners. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at using special computer models, called language models, to help grade writing assignments in massive online courses. Right now, students usually grade each other’s work, but this can be unreliable. The researchers tried a new way of teaching these computer models what to look for in good writing. They tested three different approaches and found that when the models were given correct answers and guidelines, they graded writing assignments more fairly than when students did it themselves. This could make online learning better and more efficient. |
Keywords
» Artificial intelligence » Online learning » Prompting » Zero shot
