CodeXGLUE
Canonical27papers using it
2021first seen
CodeXGLUE is a benchmark that contains a variety of code-related tasks used to evaluate the performance of models in code generation and summarization.
Papers using CodeXGLUE (27)
- Code vs Serialized AST Inputs for LLM-Based Code Summarization: An Empirical StudyMulti-task Code LLMs: Data Mix or Model Merge?Syntax Is Not Enough: An Empirical Study of Small Transformer Models for Neural Code RepairAssessing Small Language Models for Code Generation: An Empirical Study with BenchmarksAutomated Code Review Using Large Language Models with Symbolic ReasoningEnhancing Code LLM Training with Programmer AttentionShould Code Models Learn Pedagogically? A Preliminary Evaluation of
Curriculum Learning for Real-World Software Engineering TasksCodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding
and GenerationVulBERTa: Simplified Source Code Pre-Training for Vulnerability
DetectionCoTexT: Multi-task Learning with Code-Text TransformerCoSQA: 20,000+ Web Queries for Code Search and Question AnsweringA Deep Dive into Large Language Models for Automated Bug Localization
and RepairImproving ChatGPT Prompt for Code GenerationOn The Cross-Modal Transfer from Natural Language to Code through
Adapter ModulesOn using distributed representations of source code for the detection of
C security vulnerabilitiesLong-Range Modeling of Source Code Files with eWASH: Extended Window
Access by Syntax HierarchyFix Bugs with Transformer through a Neural-Symbolic Edit GrammarStructCoder: Structure-Aware Transformer for Code GenerationLongCoder: A Long-Range Pre-trained Language Model for Code CompletionProgram Translation via Code DistillationAST-T5: Structure-Aware Pretraining for Code Generation and UnderstandingReGVD: Revisiting Graph Neural Networks for Vulnerability DetectionSyntax-Aware On-the-Fly Code CompletionMultiCoder: Multi-Programming-Lingual Pre-Training for Low-Resource Code
CompletionBetter Language Models of Code through Self-ImprovementDocChecker: Bootstrapping Code Large Language Model for Detecting and
Resolving Code-Comment InconsistenciesImproving Automated Program Repair with Domain Adaptation