Summary of Beyond Scores: a Modular Rag-based System For Automatic Short Answer Scoring with Feedback, by Menna Fateen et al.
Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback
by Menna Fateen, Bo Wang, Tsunenori Mine
First submitted to arxiv on: 30 Sep 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 A novel approach to automatic short answer scoring (ASAS) with feedback is proposed, addressing the limitations of existing methods that rely heavily on fine-tuning language models. The system combines modular retrieval augmented generation and utilizes zero-shot and few-shot learning scenarios to generate detailed feedback without extensive prompt engineering. This scalable and cost-effective solution improves scoring accuracy by 9% on unseen questions compared to fine-tuning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way of grading short answers that provides helpful feedback. Right now, teachers have to spend a lot of time correcting student work, but AI can help with this task. However, current methods for giving feedback rely too much on large language models and don’t work well in different contexts. The authors suggest a new approach that uses a combination of existing techniques to generate detailed feedback without needing to train the model extensively. This approach is more efficient and accurate than previous methods. |
Keywords
» Artificial intelligence » Few shot » Fine tuning » Prompt » Retrieval augmented generation » Zero shot
