LLMCup combines multi-prompt LLM comment generation with a learned ranker, achieving 0.383 exact-match accuracy on the CUP test set versus 0.257 for HebCup and 0.177 for CUP.
A human study of comprehension and code sum- marization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLMCup: Ranking-Enhanced Comment Updating with LLMs
LLMCup combines multi-prompt LLM comment generation with a learned ranker, achieving 0.383 exact-match accuracy on the CUP test set versus 0.257 for HebCup and 0.177 for CUP.