Among 919 intro CS students solving Prompt Problems, typed prompts beat unedited voice on first-attempt success for two of three tasks; edited voice matched text, and most preferred text.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
PEFT fine-tuning of Code Llama yields feedback on student Java bugs that students judge equal to ChatGPT and better than prompt engineering, using BLEU/ROUGE/BERTScore plus human ratings.
citing papers explorer
-
Say What? Examining Text and Voice Input Modalities for Prompt-Based Programming in Computing Education
Among 919 intro CS students solving Prompt Problems, typed prompts beat unedited voice on first-attempt success for two of three tasks; edited voice matched text, and most preferred text.
-
Fine-Tuning Models for Automated Code Review Feedback
PEFT fine-tuning of Code Llama yields feedback on student Java bugs that students judge equal to ChatGPT and better than prompt engineering, using BLEU/ROUGE/BERTScore plus human ratings.