Using LLM-generated summaries as input to BERTopic can extract coherent topics from Python source code even when comments and function names are removed.
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
-
Towards Leveraging Large Language Model Summaries for Topic Modeling in Source Code
Using LLM-generated summaries as input to BERTopic can extract coherent topics from Python source code even when comments and function names are removed.