Summary of Investigating Automatic Scoring and Feedback Using Large Language Models, by Gloria Ashiya Katuka et al.
Investigating Automatic Scoring and Feedback using Large Language Models
by Gloria Ashiya Katuka, Alexander Gain, Yen-Yun Yu
First submitted to arxiv on: 1 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 paper explores the use of large language models (LLMs) like LLaMA-2 for automatic grading and feedback generation. The authors adopt parameter-efficient fine-tuning methods to decrease memory and computational requirements, leveraging classification or regression heads to fine-tune LLMs for assigning continuous numerical grades to short answers and essays, as well as generating corresponding feedback. Experiments are conducted on proprietary and open-source datasets, demonstrating high accuracy in predicting grade scores and providing graded feedback that outperforms competitive base models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at using super smart computer programs called large language models (LLMs) to automatically give grades and helpful comments on student work. To make this happen, the researchers found a way to use these powerful LLMs more efficiently, which helps reduce the need for lots of computer power. They tested this approach on different kinds of texts and found that it works really well – in fact, it’s almost as good as what expert teachers would say! This study shows how we can use new technology to make grading and feedback faster and better. |
Keywords
» Artificial intelligence » Classification » Fine tuning » Llama » Parameter efficient » Regression
