A pilot intelligent tutoring system that combines student portfolios, retrieval-augmented generation, and chain-of-thought, few-shot, and self-consistency prompting produces feedback that differs measurably from generic LLM feedback on three proxy metrics.
Better to consider data pre-pro-cessing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing tutoring systems by leveraging tailored promptings and domain knowledge with Large Language Models
A pilot intelligent tutoring system that combines student portfolios, retrieval-augmented generation, and chain-of-thought, few-shot, and self-consistency prompting produces feedback that differs measurably from generic LLM feedback on three proxy metrics.