Program Repair
33 papers with code • 3 benchmarks • 8 datasets
Task of teaching ML models to modify an existing program to fix a bug in a given code.
Datasets
Subtasks
Latest papers
Evaluating Program Repair with Semantic-Preserving Transformations: A Naturalness Assessment
In this paper, we investigate the naturalness of semantic-preserving transformations and their impacts on the evaluation of NPR.
RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair
This results in RepairLLaMA producing a highly effective `program repair adapter' for fixing bugs with language models.
Breaking the Silence: the Threats of Using LLMs in Software Engineering
Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community, impacting various SE tasks from code completion to test generation, from program repair to code summarization.
Out of Context: How important is Local Context in Neural Program Repair?
Our results indicate that overall repair success increases with the size of the local context (albeit not for all bug types) and confirm the common practice that roughly 50-60% of the input window should be used for context leading the bug.
Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair
Therefore, we propose Repilot, a general code generation framework to further copilot the AI "copilots" (i. e., LLMs) by synthesizing more valid patches during the repair process.
Graph Neural Networks For Mapping Variables Between Programs -- Extended Version
Typically, in order to compare two programs, a relation between both programs' sets of variables is required.
How Effective Are Neural Networks for Fixing Security Vulnerabilities
The results call for innovations to enhance automated Java vulnerability repair such as creating larger vulnerability repair training data, tuning LLMs with such data, and applying code simplification transformation to facilitate vulnerability repair.
xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval
Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments.
KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair
KNOD has two major novelties, including (1) a novel three-stage tree decoder, which directly generates Abstract Syntax Trees of patched code according to the inherent tree structure, and (2) a novel domain-rule distillation, which leverages syntactic and semantic rules and teacher-student distributions to explicitly inject the domain knowledge into the decoding procedure during both the training and inference phases.
Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning
In case our approach fails to determine an overfitting patch based on invariants, INVALIDATOR utilizes a trained model from labeled patches to assess patch correctness based on program syntax.