Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
Datasets
State of the Art

Support

Contact
Pricing
Terms of Service
Privacy Policy
About

© 2026 Papersgraph. All rights reserved.

Code Documentation Generation | State-of-the-Art

code-generation-1

Code Documentation Generation

3260 papers • 126 benchmarks • 313 datasets

Code Documentation Generation is a supervised task where a code function is the input to the model, and the model generates the documentation for this function. Description from: CodeTrans: Towards Cracking the Language of Silicone's Code Through Self-Supervised Deep Learning and High Performance Computing

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in code-generation-1

Trend

Dataset

Best Model

Actions

CodeSearchNet - Java

CodeSearchNet - Java

CodeSearchNet - Php

CodeSearchNet - Php

CodeSearchNet - JavaScript

Libraries

i

Use these libraries to find code-generation-1 models and implementations

Datasets

No datasets available.

Subtasks

CodeSearchNet - Java

Most implemented papers

CodeBERT: A Pre-Trained Model for Programming and Natural Languages

Daya Guo, Daxin Jiang, Duyu Tang, Linjun Shou, Ming Gong, Ming Zhou, Nan Duan, Ting Liu, Bing Qin, Zhangyin Feng, Xiaocheng Feng•Tue Feb 18 2020

This work develops CodeBERT with Transformer-based neural architecture, and trains it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators.

3490

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

CodeSearchNet - JavaScript

CodeSearchNet - Python

CodeSearchNet - Python

CodeSearchNet - Go

CodeSearchNet - Go

CodeSearchNet - Ruby

CodeSearchNet - Ruby

CodeSearchNet

CodeSearchNet

0

HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks

Lingfei Wu, Dakuo Wang, Xuye Liu, A. Wang•Tue Mar 30 2021

A new model is proposed (HAConvGNN) that uses a hierarchical attention mechanism to consider therelevant code cells and the relevant code tokens information when generating the documentation in computational notebooks.

25 0

Memorization and Generalization in Neural Code Intelligence Models

Mohammad Amin Alipour, Md Rafiqul Islam Rabin, Aftab Hussain, Vincent J. Hellendoorn•Tue Jun 15 2021

This work evaluates the memorization and generalization tendencies in neural code intelligence models through a case study across several benchmarks and model families by leveraging established approaches from other fields that use DNNs, such as introducing targeted noise into the training dataset.

48 0

Assemble Foundation Models for Automatic Code Summarization

Jian Gu, P. Salza, H. Gall•Wed Jan 12 2022

This work assembles available foundation models, such as CodeBERT and GPT-2, into a single model named AdaMo, and utilizes Gaussian noise as the simulation of contextual information to optimize the latent representation.

44 0

RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation

Maosong Sun, Yankai Lin, Yining Ye, Yujia Qin, Shihao Liang, Xin Cong, Zhong Zhang, Yesai Wu, Ya-Ting Lu, Qinyu Luo, Yingli Zhang, Xiaoyin Che, Zhiyuan Liu•Sun Feb 25 2024

RepoAgent, a large language model powered open-source framework aimed at proactively generating, maintaining, and updating code documentation, is introduced, showing that RepoAgent excels in generating high-quality repository-level documentation.

78 0

ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Deep Learning and High Performance Computing

Llion Jones, Christian Dallago, Ahmed Elnaggar, M. Heinzinger, G. Rehawi, Yu Wang, Tom Gibbs, Tamas B. Fehér, Christoph Angerer, Martin Steinegger, D. Bhowmik, B. Rost•Sat Jul 11 2020

Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models (LMs) taken from Natural Language Processing (NLP). These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive language models (Transformer-XL, XLNet) and two auto-encoder models (Bert, Albert) on data from UniRef and BFD containing up to 393 billion amino acids (words) from 2.1 billion protein sequences (22- and 112-times the entire English Wikipedia). The LMs were trained on the Summit supercomputer at Oak Ridge National Laboratory (ORNL), using 936 nodes (total 5616 GPUs) and one TPU Pod (V3-512 or V3-1024). We validated the advantage of up-scaling LMs to larger models supported by bigger data by predicting secondary structure (3-states: Q3=76-84, 8-states: Q8=65-73), sub-cellular localization for 10 cellular compartments (Q10=74) and whether a protein is membrane-bound or water-soluble (Q2=89). Dimensionality reduction revealed that the LM-embeddings from unlabeled data (only protein sequences) captured important biophysical properties governing protein shape. This implied learning some of the grammar of the language of life realized in protein sequences. The successful up-scaling of protein LMs through HPC to larger data sets slightly reduced the gap between models trained on evolutionary information and LMs.

1178 0

Adding a benchmark result helps the community track progress.