Paper
When LLMs Help -- and Hurt -- Teaching Assistants in Proof-Based Courses
Authors
Romina Mahinpei, Sofiia Druchyna, Manoel Horta Ribeiro
Abstract
Teaching assistants (TAs) are essential to grading and feedback provision in proof-based courses, yet these tasks are time-intensive and difficult to scale. Although Large Language Models (LLMs) have been studied for grading and feedback, their effectiveness in proof-based courses is still unknown. Before designing LLM-based systems for this context, a necessary prerequisite is to understand whether LLMs can meaningfully assist TAs with grading and feedback. As such, we present a multi-part case study functioning as a technology probe in an undergraduate proof-based course. We compare rubric-based grading decisions made by an LLM and TAs with varying levels of expertise and examine TAs' perceptions of feedback generated by an LLM. We find substantial disagreement between LLMs and TAs on grading decisions but that LLM-generated feedback can still be useful to TAs for submissions with major errors. We conclude by discussing design implications for human-AI grading and feedback systems in proof-based courses.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.23635v1</id>\n <title>When LLMs Help -- and Hurt -- Teaching Assistants in Proof-Based Courses</title>\n <updated>2026-02-27T03:13:52Z</updated>\n <link href='https://arxiv.org/abs/2602.23635v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.23635v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Teaching assistants (TAs) are essential to grading and feedback provision in proof-based courses, yet these tasks are time-intensive and difficult to scale. Although Large Language Models (LLMs) have been studied for grading and feedback, their effectiveness in proof-based courses is still unknown. Before designing LLM-based systems for this context, a necessary prerequisite is to understand whether LLMs can meaningfully assist TAs with grading and feedback. As such, we present a multi-part case study functioning as a technology probe in an undergraduate proof-based course. We compare rubric-based grading decisions made by an LLM and TAs with varying levels of expertise and examine TAs' perceptions of feedback generated by an LLM. We find substantial disagreement between LLMs and TAs on grading decisions but that LLM-generated feedback can still be useful to TAs for submissions with major errors. We conclude by discussing design implications for human-AI grading and feedback systems in proof-based courses.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n <published>2026-02-27T03:13:52Z</published>\n <arxiv:primary_category term='cs.HC'/>\n <author>\n <name>Romina Mahinpei</name>\n </author>\n <author>\n <name>Sofiia Druchyna</name>\n </author>\n <author>\n <name>Manoel Horta Ribeiro</name>\n </author>\n </entry>"
}