In-ide code generation from natural language: Promise and challenges

FF Xu, B Vasilescu, G Neubig - ACM Transactions on Software …, 2022 - dl.acm.org
A great part of software development involves conceptualizing or communicating the
underlying procedures and logic that needs to be expressed in programs. One major …

Docprompting: Generating code by retrieving the docs

S Zhou, U Alon, FF Xu, Z Wang, Z Jiang… - arXiv preprint arXiv …, 2022 - arxiv.org
Publicly available source-code libraries are continuously growing and changing. This makes
it impossible for models of code to keep current with all available APIs by simply training …

Toolcoder: Teach code generation models to use api search tools

K Zhang, H Zhang, G Li, J Li, Z Li, Z Jin - arXiv preprint arXiv:2305.04032, 2023 - arxiv.org
Automatically generating source code from natural language descriptions has been a
growing field of research in recent years. However, current large-scale code generation …

MultiPL-E: a scalable and polyglot approach to benchmarking neural code generation

F Cassano, J Gouwar, D Nguyen… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Large language models have demonstrated the ability to generate both natural language
and programming language text. Although contemporary code generation models are …

Multipl-e: A scalable and extensible approach to benchmarking neural code generation

F Cassano, J Gouwar, D Nguyen, S Nguyen… - arXiv preprint arXiv …, 2022 - arxiv.org
Large language models have demonstrated the ability to generate both natural language
and programming language text. Such models open up the possibility of multi-language …

Codegeex: A pre-trained model for code generation with multilingual benchmarking on humaneval-x

Q Zheng, X Xia, X Zou, Y Dong, S Wang… - Proceedings of the 29th …, 2023 - dl.acm.org
Large pre-trained code generation models, such as OpenAI Codex, can generate syntax-
and function-correct code, making the coding of programmers more productive. In this paper …

Incorporating external knowledge through pre-training for natural language to code generation

FF Xu, Z Jiang, P Yin, B Vasilescu, G Neubig - arXiv preprint arXiv …, 2020 - arxiv.org
Open-domain code generation aims to generate code in a general-purpose programming
language (such as Python) from natural language (NL) intents. Motivated by the intuition that …

Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models

P Vaithilingam, T Zhang, EL Glassman - Chi conference on human …, 2022 - dl.acm.org
Recent advances in Large Language Models (LLM) have made automatic code generation
possible for real-world programming tasks in general-purpose programming languages …

Retrieval on source code: a neural code search

S Sachdev, H Li, S Luan, S Kim, K Sen… - Proceedings of the 2nd …, 2018 - dl.acm.org
Searching over large code corpora can be a powerful productivity tool for both beginner and
experienced developers because it helps them quickly find examples of code related to their …

In-ide generation-based information support with a large language model

D Nam, A Macvean, V Hellendoorn, B Vasilescu… - arXiv preprint arXiv …, 2023 - arxiv.org
Developers often face challenges in code understanding, which is crucial for building and
maintaining high-quality software systems. Code comments and documentation can provide …