CoNaLa

CoNaLa Dataset for Code Generation Table of content Dataset Description Languages Dataset Structure Data Instances Data Fields Data Splits Dataset Descritpion This dataset has been processed for Code Generation. CMU CoNaLa, the Code/Natural Language Challenge is a joint project of the Carnegie Mellon University NeuLab

Papers using CoNaLa (11)

Cross-Task Benchmarking and Evaluation of General-Purpose and Code-Specific Large Language Models2025DocPrompting: Generating Code by Retrieving the Docs2022 · 19 citesRelevance Transformer: Generating Concise Code Snippets with Relevance Feedback2020 · 18 citesExploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models2023 · 12 citesGenerating Code with the Help of Retrieved Template Functions and Stack Overflow Answers2021 · 6 citesCodePAD: Sequence-based Code Generation with Pushdown Automaton2022 · 4 citesMCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages2022 · 2 citesUncovering Weaknesses in Neural Code Generation2024 · 2 citesNatural Language to Code Using Transformers2022 · 1 citesReading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation2021Text Classification for Task-based Source Code Related Questions2021