natural-language-processing-3

Class-level Code Generation

3260 papers • 126 benchmarks • 313 datasets

a task to generate the class-level code based on input description

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in class-level-code-generation-6

Trend

Dataset

Best Model

Actions

RESIDE TestSet-S

Libraries

i

Use these libraries to find class-level-code-generation-6 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

pix2code: Generating Code from a Graphical User Interface Screenshot

Tony Beltramelli•Sun May 21 2017

It is shown that deep learning methods can be leveraged to train a model end-to-end to automatically reverse engineer user interfaces and generate code from a single input image with over 77% of accuracy for three different platforms.

328

Content

0

Paper Graph

ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation

Xueying Du, Kaixin Wang, Mingwei Liu, Junwei Liu, Yixuan Chen, Jiayi Feng, Hanlin Wang, Chaofeng Sha, Xin Peng, Yiling Lou•Wed Aug 02 2023

This work makes the first attempt to evaluate LLMs in a more challenging code generation scenario, i.e. class-level code generation, and finds the limited model ability of generating method-dependent code and discusses the frequent error types in generated classes.

199 0

Paper Graph

Adding a benchmark result helps the community track progress.