SOTAVerified

Program Repair

Task of teaching ML models to modify an existing program to fix a bug in a given code.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 132 papers

TitleStatusHype
Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments—0
To Err is Machine: Vulnerability Detection Challenges LLM Reasoning—0
RepairAgent: An Autonomous, LLM-Based Agent for Program RepairCode2
A Study of Vulnerability Repair in JavaScript Programs with Large Language Models—0
DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models—0
Towards Reliable Evaluation of Neural Program Repair with Natural Robustness TestingCode0
A Novel Approach for Automatic Program Repair using Round-Trip Translation with Large Language ModelsCode0
RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program RepairCode1
Breaking the Silence: the Threats of Using LLMs in Software EngineeringCode0
Out of Context: How important is Local Context in Neural Program Repair?Code0
Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning—0
ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair—0
Enhancing Genetic Improvement Mutations Using Large Language ModelsCode1
Automated Bug Generation in the era of Large Language Models—0
Program Repair with Minimal Edits Using CodeT5—0
Frustrated with Code Quality Issues? LLMs can Help!—0
RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair—0
Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program RepairCode1
Graph Neural Networks For Mapping Variables Between Programs -- Extended VersionCode0
An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code—0
Better patching using LLM prompting, via Self-Consistency—0
How Effective Are Neural Networks for Fixing Security VulnerabilitiesCode1
Is ChatGPT the Ultimate Programming Assistant -- How far is it?—0
Fully Autonomous Programming with Large Language Models—0
Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering—0
Show:102550
← PrevPage 3 of 6Next →
All datasetsDeepFixGitHub-PythonHumanEvalPackTFix's Code Patches Data

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DrRepair + BIFIAverage Success Rate71.7—Unverified
2DrRepairAverage Success Rate68.2—Unverified
3SampleFixAverage Success Rate45.3—Unverified
4RLAssistAverage Success Rate26.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer + BIFIAccuracy (%)90.5—Unverified
2TransformerAccuracy (%)62—Unverified
#ModelMetricClaimedVerifiedStatus
1MGDebugger (DeepSeek-Coder-V2-Lite)Pass@197.6—Unverified
#ModelMetricClaimedVerifiedStatus
1TFixError Removal678—Unverified