A systematic review that categorizes prompting strategies for LLM-based code summarization, assesses their effectiveness, and identifies gaps in research and evaluation practices.
Commenting higher-level code unit: Full code, reduced code, or hierarchical code summarization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The study tests the feasibility of supplying design documents as context to LLMs to produce more useful code comments for novice-created codebases.
citing papers explorer
-
Prompt-Driven Code Summarization: A Systematic Literature Review
A systematic review that categorizes prompting strategies for LLM-based code summarization, assesses their effectiveness, and identifies gaps in research and evaluation practices.
-
Leveraging Design-Aware Context in Large Language Models for Code Comment Generation
The study tests the feasibility of supplying design documents as context to LLMs to produce more useful code comments for novice-created codebases.