Benchmarking Causal Study to Interpret Large Language Models for Source Code.
Daniel Rodríguez-CárdenasDavid N. PalacioDipin KhatiHenry BurkeDenys PoshyvanykPublished in: ICSME (2023)
Keyphrases
- source code
- language model
- language modeling
- open source
- software maintenance
- probabilistic model
- document retrieval
- software systems
- open source software
- n gram
- test collection
- information retrieval
- software projects
- retrieval model
- query expansion
- natural language
- impact analysis
- real world
- software evolution
- mailing lists
- legacy systems
- smoothing methods
- automated tools
- statistical language models
- free software
- manual inspection
- source files