A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science

Abstract

This paper explores the use of large language models (LLMs) to score and explain short-answer assessments in K-12 science. While existing methods can score more structured math and computer science assessments, they often do not provide explanations for the scores. Our study focuses on employing GPT-4 for automated assessment in middle school Earth Science, combining few-shot and active learning with chain-of-thought reasoning. Using a human-in-the-loop approach, we successfully score and provide meaningful explanations for formative assessment responses. A systematic analysis of our method's pros and cons sheds light on the potential for human-in-the-loop techniques to enhance automated grading for open-ended science assessments.

Cite

Text

Cohn et al. "A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30364

Markdown

[Cohn et al. "A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/cohn2024aaai-chain/) doi:10.1609/AAAI.V38I21.30364

BibTeX

@inproceedings{cohn2024aaai-chain,
  title     = {{A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science}},
  author    = {Cohn, Clayton and Hutchins, Nicole and Le, Tuan and Biswas, Gautam},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23182-23190},
  doi       = {10.1609/AAAI.V38I21.30364},
  url       = {https://mlanthology.org/aaai/2024/cohn2024aaai-chain/}
}