In terms of feedback, students actually seem to slightly *prefer* feedback written by LLMs over human-written feedback. While there is some nuance to this result, the conclusion is clear: students are just as happy with LLM-generated feedback as with TA-written feedback. 5/

In our setup, LLMs determined whether answers satisfied predefined grading criteria that we, TAs, painstakingly prepared ahead of time. Here, LLMs achieve about ~90% accuracy. Small LLMs work well on easier questions but are overly generous for harder and open-ended questions. 4/

Can LLMs replace human teaching assistants in grading homework assignments?
This semester, we ran a study in our Bioinformatics course with 100+ enrolled master's students, whose assignments were graded by 6 LLMs. 1/