Compositional API Recommendation for Library-Oriented Code Generation

arXiv:2402.19431v1 Announce Type: cross
Abstract: Large language models (LLMs) have achieved exceptional performance in code generation. However, the performance remains unsatisfactory in generating library-oriented code, especially for the libraries not present in the training data of LLMs. Previous work utilizes API recommendation technology to help LLMs use libraries: it retrieves APIs related to the user requirements, then leverages them as context to prompt LLMs. However, developmental requirements can be coarse-grained, requiring a combination of multiple fine-grained APIs. This granularity inconsistency …

abstract api apis arxiv code code generation cs.ai cs.cl cs.se data language language models large language large language models libraries library llms performance recommendation technology training training data type work