Summary of Veras: Verify Then Assess Stem Lab Reports, by Berk Atil et al.
VerAs: Verify then Assess STEM Lab Reports
by Berk Atil, Mahsa Sheikhi Karizaki, Rebecca J. Passonneau
First submitted to arxiv on: 7 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); 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 proposed end-to-end neural architecture, dubbed VerAs, tackles the challenge of automated assessment of long-form writing in STEM subjects. Specifically, it focuses on lab reports from an inquiry-based physics curriculum, which are crucial for developing critical thinking skills. The model consists of a verifier module and an assessment module, both inspired by Open Domain Question Answering (OpenQA) approaches. VerAs first verifies the presence of relevant content regarding a specific rubric dimension before assessing the relevant sentences. In experiments on college-level lab reports and middle school physics essays, VerAs outperforms various baselines based on OpenQA systems or Automated Essay Scoring (AES). This work demonstrates the potential for AI-powered tools to support STEM education by providing detailed feedback to students. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers has created a special tool to help teachers grade lab reports in science class. Lab reports are important because they help students learn how to think critically about scientific questions. The tool, called VerAs, uses artificial intelligence (AI) to check if the report answers specific questions and then gives feedback on what’s good or bad. This helps students improve their writing skills. The AI model is tested on lab reports from college and middle school physics classes and performs better than other grading tools. |
Keywords
* Artificial intelligence * Question answering
