Summary of Rationale Behind Essay Scores: Enhancing S-llm’s Multi-trait Essay Scoring with Rationale Generated by Llms, By Seongyeub Chu et al.
Rationale Behind Essay Scores: Enhancing S-LLM’s Multi-Trait Essay Scoring with Rationale Generated by LLMs
by SeongYeub Chu, JongWoo Kim, Bryan Wong, MunYong Yi
First submitted to arxiv on: 18 Oct 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 novel Rationale-based Multiple Trait Scoring (RMTS) approach combines large language models (LLMs) and a fine-tuning-based essay scoring model to accurately predict multi-trait scores. This method uses LLMs to generate trait-specific rationales based on rubric guidelines, which are then used by the scoring model to make predictions. RMTS outperforms state-of-the-art models and vanilla S-LLMs in extensive experiments on benchmark datasets such as ASAP, ASAP++, and Feedback Prize. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Automated essay scoring (AES) is getting better! A new approach called RMTS uses big language models to help score essays based on specific traits. It’s like having a super smart tutor that can explain why it gave you a certain grade. The results show that this method works really well and provides more reliable scores. |
Keywords
» Artificial intelligence » Fine tuning
