Defects4J
Canonical84papers using it
2018first seen
Defects4J is a benchmark dataset that contains a collection of real-world Java bugs used to evaluate fault localization techniques.
Papers using Defects4J (83)
- Are Large Language Models Memorizing Bug Benchmarks?Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding HeadsLLM-based Mockless Unit Test Generation for JavaThe Impact of Fine-tuning Large Language Models on Automated Program RepairHyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at ScaleRuntime Execution Traces Guided Automated Program Repair with Multi-Agent DebateProject Prometheus: Bridging the Intent Gap in Agentic Program Repair via Reverse-Engineered Executable SpecificationsDebugRepair: Enhancing LLM-Based Automated Program Repair via Self-Directed DebuggingAgentic Code ReasoningBoosting LLMs for Mutation GenerationSpecification Vibing for Automated Program RepairHAFixAgent: History-Aware Program Repair AgentEnhancing LLM-based Fault Localization with a Functionality-Aware Retrieval-Augmented Generation FrameworkBloomAPR: A Bloom's Taxonomy-based Framework for Assessing the Capabilities of LLM-Powered APR SolutionsReinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code GenerationBreaking the Myth: Can Small Models Infer Postconditions Too?Improving LLM-Based Fault Localization with External Memory and Project ContextHAFixAgent: History-Aware Automated Program Repair AgentThe Art of Repair: Optimizing Iterative Program Repair with
Instruction-Tuned ModelsAssessing the Impact of Code Changes on the Fault Localizability of Large Language ModelsEvaluating the Generalizability of LLMs in Automated Program RepairLLMs are Bug Replicators: An Empirical Study on LLMs' Capability in
Completing Bug-prone CodeStudying and Understanding the Effectiveness and Failures of
Conversational LLM-Based RepairWhere's the Bug? Attention Probing for Scalable Fault LocalizationHAFix: History-Augmented Large Language Models for Bug FixingFlexFL: Flexible and Effective Fault Localization with Open-Source Large
Language ModelsExploring and Lifting the Robustness of LLM-powered Automated Program
Repair with Metamorphic TestingContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case PairsBoosting Redundancy-based Automated Program Repair by Fine-grained Pattern MiningSequenceR: Sequence-to-Sequence Learning for End-to-End Program RepairTBar: Revisiting Template-based Automated Program RepairCURE: Code-Aware Neural Machine Translation for Automatic Program RepairLess Training, More Repairing Please: Revisiting Automated Program
Repair via Zero-shot LearningiFixR: Bug Report driven Program RepairSelfAPR: Self-supervised Program Repair with Test Execution DiagnosticsA Deep Dive into Large Language Models for Automated Bug Localization
and RepairAlleviating Patch Overfitting with Automatic Test Generation: A Study of
Feasibility and Effectiveness for the Nopol Repair SystemExtracting Concise Bug-Fixing Patches from Human-Written Patches in
Version Control SystemsThinkRepair: Self-Directed Automated Program RepairHow Different Is It Between Machine-Generated and Developer-Provided
Patches? An Empirical Study on The Correct Patches Generated by Automated
Program Repair TechniquesLarge Language Models in Fault LocalisationRepairAgent: An Autonomous, LLM-Based Agent for Program RepairDEAR: A Novel Deep Learning-based Approach for Automated Program RepairENCORE: Ensemble Learning using Convolution Neural Machine Translation
for Automatic Program RepairDomain Adaptation for Code Model-based Unit Test Case GenerationUnit Test Case Generation with Transformers and Focal ContextCigaR: Cost-efficient Program Repair with LLMsLarge Language Models are Few-shot Testers: Exploring LLM-based General
Bug ReproductionTowards Generating Functionally Correct Code Edits from Natural Language
Issue DescriptionsAPPT: Boosting Automated Patch Correctness Prediction via Fine-tuning
Pre-trained ModelsLarge Language Models for Test-Free Fault LocalizationUniDebugger: Hierarchical Multi-Agent Framework for Unified Software DebuggingRevisiting ssFix for Better Program RepairMCRepair: Multi-Chunk Program Repair via Patch Optimization with Buggy
BlockPractical Program Repair via Bytecode MutationHarnessing Evolution for Multi-Hunk Program RepairCan Automated Program Repair Refine Fault Localization?Can LLMs Demystify Bug Reports?Enriching Automatic Test Case Generation by Extracting Relevant Test
Inputs from Bug ReportsRESTORE: Retrospective Fault Localization Enhancing Automated Program
RepairBetter Automatic Program Repair by Using Bug Reports and Tests TogetherAdversarial Patch Generation for Automated Program RepairEvaluating Diverse Large Language Models for Automatic and General Bug
ReproductionBugsInPy: A Database of Existing Bugs in Python Programs to Enable
Controlled Testing and Debugging StudiesRepairBench: Leaderboard of Frontier Models for Program RepairHyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks
at ScaleAttention Please: Consider Mockito when Evaluating Newly Proposed
Automated Program Repair TechniquesAVATAR : Fixing Semantic Bugs with Fix Patterns of Static Analysis
ViolationsAutomated Classification of Overfitting Patches with Statically
Extracted Code FeaturesElixir: Effective object-oriented program repairA Quick Repair Facility for DebuggingReinforcement Learning for Mutation Operator Selection in Automated
Program RepairThe GitHub Recent Bugs Dataset for Evaluating LLM-based Debugging
ApplicationsGitBug-Actions: Building Reproducible Bug-Fix Benchmarks with GitHub
ActionsAligning the Objective of LLM-based Program RepairOn The Effectiveness of Dynamic Reduction Techniques in Automated
Program RepairImpact of Large Language Models of Code on Fault LocalizationRevisiting Evolutionary Program Repair via Code Language ModelMemory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch GenerationSoftware Fault Localization Based on Multi-objective Feature Fusion and
Deep LearningWhat You See Is What You Get: Attention-based Self-guided Automatic Unit
Test GenerationUsing Defect Prediction to Improve the Bug Detection Capability of
Search-Based Software TestingNeural-Based Test Oracle Generation: A Large-scale Evaluation and
Lessons Learned