Summary of Rdbe: Reasoning Distillation-based Evaluation Enhances Automatic Essay Scoring, by Ali Ghiasvand Mohammadkhani
RDBE: Reasoning Distillation-Based Evaluation Enhances Automatic Essay Scoring
by Ali Ghiasvand Mohammadkhani
First submitted to arxiv on: 3 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Computers and Society (cs.CY); 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 introduces Reasoning Distillation-Based Evaluation (RDBE), an innovative approach to automatic essay scoring that not only generates scores but also provides interpretability into the reasoning behind those scores. By leveraging a large language model’s generated reasoning, RDBE trains a small language model to distill this reasoning and enhance its performance. The results demonstrate the effectiveness of RDBE across various scoring rubrics, outperforming both zero-shot large language model generation and fine-tuned baseline models. This showcases RDBE’s practical interpretative output and enhanced performance in automatic essay scoring. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to score essays using artificial intelligence. Instead of just giving a grade, the AI also explains why it gave that grade. The researchers used a big language model to help train a smaller one to do this. They tested their method on many different rubrics and found that it did better than other methods. This is important because it can help teachers understand why the AI is grading essays in certain ways, which can be helpful for learning. |
Keywords
* Artificial intelligence * Distillation * Language model * Large language model * Zero shot
