Bug fixing
25 papers with code • 1 benchmarks • 1 datasets
Benchmarks
These leaderboards are used to track progress in Bug fixing
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
SWE-bench-lite
Most implemented papers
GPT-4 Technical Report
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs.
Neural Transfer Learning for Repairing Security Vulnerabilities in C Code
To sum up, this paper shows that transfer learning works well for repairing security vulnerabilities in C compared to learning on a small dataset.
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
We find real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models.
AutoCodeRover: Autonomous Program Improvement
Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use LLM-based programming assistants to achieve automated coding.
Learning the Relation between Code Features and Code Transforms with Structured Prediction
We instantiate our approach in the context of repair transform prediction for Java programs.
Empirical Study of Transformers for Source Code
bayesgroup/code_transformers
•
•
In this work, we conduct a thorough empirical study of the capabilities of Transformers to utilize syntactic information in different tasks.
On the Embeddings of Variables in Recurrent Neural Networks for Source Code
nadiinchi/dynamic_embeddings
•
•
NAACL 2021
In this work, we develop dynamic embeddings, a recurrent mechanism that adjusts the learned semantics of the variable when it obtains more information about the variable's role in the program.
A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code
bayesgroup/code_transformers
•
•
NAACL 2021
There is an emerging interest in the application of natural language processing models to source code processing tasks.
D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis
However, existing datasets to train models for vulnerability identification suffer from multiple limitations such as limited bug context, limited size, and synthetic and unrealistic source code.
DABT: A Dependency-aware Bug Triaging Method
In software engineering practice, fixing a bug promptly reduces the associated costs.
