Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course

TL;DR

This study explores the use of GPT-4 as an automatic assignment evaluator in a large university course, revealing its acceptability, limitations, and potential for future improvement in educational settings.

Contribution

It provides empirical insights into applying LLMs for assignment evaluation in real classrooms, highlighting challenges and offering practical recommendations.

Findings

Students accept LLM evaluation with free access.

LLMs sometimes fail to follow evaluation instructions.

Students can manipulate LLM outputs to achieve high scores.

Abstract

Using large language models (LLMs) for automatic evaluation has become an important evaluation method in NLP research. However, it is unclear whether these LLM-based evaluators can be applied in real-world classrooms to assess student assignments. This empirical report shares how we use GPT-4 as an automatic assignment evaluator in a university course with 1,028 students. Based on student responses, we find that LLM-based assignment evaluators are generally acceptable to students when students have free access to these LLM-based evaluators. However, students also noted that the LLM sometimes fails to adhere to the evaluation instructions. Additionally, we observe that students can easily manipulate the LLM-based evaluator to output specific strings, allowing them to achieve high scores without meeting the assignment rubric. Based on student feedback and our experience, we provide several recommendations for integrating LLM-based evaluators into future classrooms. Our observation also highlights potential directions for improving LLM-based evaluators, including their instruction-following ability and vulnerability to prompt hacking.