Summary of Human-ai Collaborative Essay Scoring: a Dual-process Framework with Llms, by Changrong Xiao et al.
Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMs
by Changrong Xiao, Wenxing Ma, Qingping Song, Sean Xin Xu, Kunpeng Zhang, Yufang Wang, Qi Fu
First submitted to arxiv on: 12 Jan 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 This study investigates the application of Large Language Models (LLMs) in Automated Essay Scoring (AES). The researchers compared proprietary and open-source LLMs on public and private datasets, finding that while they don’t surpass conventional models in performance, they exhibit consistency, generalizability, and explainability. A proposed open-source LLM-based AES system offers accurate grading and high-quality feedback, comparable to fine-tuned proprietary LLMs. The system also automates the grading process, enhancing human graders’ performance and efficiency, particularly for essays with lower model confidence. The results demonstrate the potential of LLMs in facilitating human-AI collaboration in education, transforming learning experiences through AI-generated feedback. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how computers can help grade school essays when humans aren’t available. Researchers tested different language models on various datasets and found that while they’re not perfect, they can still provide helpful feedback. They created a new system that uses these models to grade essays accurately and give high-quality feedback. This system helps both human graders and students by making the grading process more efficient and accurate. |
