Building a Coding Assistant via the Retrieval-Augmented Language Model

Xinze Li

doi:10.1145/3695868

Building a Coding Assistant via the Retrieval-Augmented Language Model

2025-01-17

1

PRE

AI

DOI：10.1145/3695868

Original request for help

Save

Abstract

En 中文

Pretrained language models have shown strong effectiveness in code-related tasks, such as code retrieval, code generation, code summarization, and code completion tasks. In this article, we propose COde assistaNt viA retrieval-augmeNted language model (CONAN), which aims to build a code assistant by mimicking the knowledge-seeking behaviors of humans during coding. Specifically, it consists of a code structure- aware retriever (CONAN-R) and a dual-view code representation-based retrieval-augmented generation model (CONAN-G). CONAN-R pretrains CodeT5 using Code-Documentation Alignment and Masked Entity Prediction tasks to make language models code structure-aware and learn effective representations for code snippets and documentation. Then CONAN-G designs a dual-view code representation mechanism for implementing a retrieval-augmented code generation model. CONAN-G regards the code documentation

Building a Coding Assistant via the Retrieval-Augmented Language Model

Abstract

Journal

Organization