• Home
  • Search
  • Retrieval Augmented Code Generation and Summarization
  • https://doi.org/10.48448/r5xk-zd87Copy DOI Icon

Retrieval Augmented Code Generation and Summarization

  • Oct 21, 2021
  • Underline Science Inc.
  • The 2021 Conference On Empirical Methods In Natural Language Processing 2021
Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Software developers write a lot of source code and documentation during software development. Intrinsically, developers often recall parts of source code or code summaries that they had written in the past while implementing software or documenting them. To mimic developers' code or summary generation behavior, we propose a retrieval augmented framework, REDCODER, that retrieves relevant code or summaries from a retrieval database and provides them as a supplement to code generation or summarization models. REDCODER has a couple of uniqueness. First, it extends the state-of-the-art dense retrieval technique to search for relevant code or summaries. Second, it can work with retrieval databases that include unimodal (only code or natural language description) or bimodal instances (code-description pairs). We conduct experiments and extensive analysis on two benchmark datasets of code generation and summarization in Java and Python, and the promising results endorse the effectiveness of our proposed retrieval augmented framework.

Similar Papers
  • Conference Article
  • Citations78

Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning

  • Apr 20, 2020
  • Wei Ye +5
  • Video Transcripts

Unified Pre-training for Program Understanding and Generation

  • May 25, 2021
  • Underline Science Inc.
  • Saikat Chakraborty
  • Video Transcripts

CoDesc: A Large Code–Description Parallel Dataset

  • Aug 03, 2021
  • Underline Science Inc.
  • Masum Hasan +1
  • Research Article
  • Citations7

COFFE: A Code Efficiency Benchmark for Code Generation

  • Jun 19, 2025
  • Proceedings of the ACM on Software Engineering
  • Yun Peng +3
  • Research Article
  • Citations8

Building a Coding Assistant via the Retrieval-Augmented Language Model

  • Jan 17, 2025
  • ACM Transactions on Information Systems
  • Xinze Li +8
  • Research Article

Evaluating Programming Resources: The Impact of Code Generators in Software Development

  • Sep 01, 2024
  • Journal of Software Engineering and Simulation
  • Herny Februariyanti +3
  • Research Article
  • Citations2

Towards Secure Code Generation With LLMs: A Study on Common Weakness Enumeration

  • Dec 01, 2025
  • IEEE Transactions on Software Engineering
  • Jianguo Zhao +6
  • Research Article
  • Citations1

AI-Powered Code Generation Evaluating the Effectiveness of Large Language Models (LLMs) in Automated Software Development

  • Mar 31, 2023
  • Journal of Artificial Intelligence & Cloud Computing
  • Ravikanth Konda
  • Conference Article

AutoFlowgen: A Multi-Agent Framework for Automated Generation of Workflows from Natural Language

  • Jun 20, 2025
  • Zhongjun Yang +5
  • Research Article

State of the Art of the Security of Code Generated by LLMs: A Multivocal Literature Review

  • Dec 01, 2025
  • Programming and Computer Software
  • Leonardo Criollo Ramírez +3
  • PDF
  • Research Article
  • Citations12

DeviceTalk: A No-Code Low-Code IoT Device Code Generation

  • Jun 30, 2022
  • Sensors (Basel, Switzerland)
  • Whai-En Chen +4
  • Research Article
  • Citations135

Retargetable Code Generation Based on Structural Processor Description

  • Jan 01, 1998
  • Design Automation for Embedded Systems
  • Rainer Leupers +1
  • Research Article

Improving Code Generation Based on LoRA Fine-Tuning

  • Dec 31, 2025
  • Applied and Computational Engineering
  • Yuanfan Zhao
  • Research Article
  • Citations6

Can large language models generate geospatial code?

  • Aug 03, 2025
  • Geo-spatial Information Science
  • Shuyang Hou +10
  • Conference Article
  • Citations6

Automatic Code Generation From Low Fidelity Graphical User Interface Sketches Using Deep Learning

  • Nov 28, 2022
  • Biniam Behailu Adefris +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.