Analysis of student-LLM conversations and code in a 13-week software engineering course finds ChatGPT preferred over Copilot and conversational prompting yields lower-complexity code.
Few-shot training llms for project- specific code-summarization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Analysis of Student-LLM Interaction in a Software Engineering Project
Analysis of student-LLM conversations and code in a 13-week software engineering course finds ChatGPT preferred over Copilot and conversational prompting yields lower-complexity code.