Neural metrics for evaluating code comments are unreliable for multilingual output, often scoring random noise as high as real generated comments.
Title resolution pending
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
-
A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics
Neural metrics for evaluating code comments are unreliable for multilingual output, often scoring random noise as high as real generated comments.