{"total":29,"rows":[{"id":"2403.18105","title":"Large Language Models for Education: A Survey and Outlook","created":"2024-03-26","cited_by_count":188,"area":null},{"id":"2403.18746","title":"CYCLE: Learning to Self-Refine the Code Generation","created":"2024-03-27","cited_by_count":42,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36,"area":null},{"id":"2411.01414","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2411.06638","title":"Model Editing for LLMs4Code: How Far are We?","created":"2024-11-11","cited_by_count":10,"area":null},{"id":"2503.05012","title":"LLMs' Reshaping of People, Processes, Products, and Society in Software Development: A Comprehensive Exploration with Early Adopters","created":"2025-03-06","cited_by_count":8,"area":null},{"id":"2411.10129","title":"Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation","created":"2024-11-15","cited_by_count":7,"area":null},{"id":"2411.15501","title":"Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2504.19444","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2407.04868","title":"Looking into Black Box Code Language Models","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2409.10959","title":"Leveraging Reviewer Experience in Code Review Comment Generation","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2401.07518","title":"Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2404.09066","title":"CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistants","created":"2024-04-13","cited_by_count":3,"area":null},{"id":"2503.16167","title":"CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2510.17389","title":"EduAdapt: A Question Answer Benchmark Dataset for Evaluating Grade-Level Adaptability in LLMs","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2505.14976","title":"SDLog: A Deep Learning Framework for Detecting Sensitive Information in Software Logs","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2509.04810","title":"Code Review Without Borders: Evaluating Synthetic vs. Real Data for Review Recommendation","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2604.24525","title":"Understanding the Limits of Automated Evaluation for Code Review Bots in Practice","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2503.00673","title":"Towards Refining Developer Questions using LLM-Based Named Entity Recognition for Developer Chatroom Conversations","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2503.16144","title":"Unify and Triumph: Polyglot, Diverse, and Self-Consistent Generation of Unit Tests with LLMs","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2507.19271","title":"Fine-Tuning Multilingual Language Models for Code Review: An Empirical Study on Industrial C# Projects","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2507.21954","title":"Fine-Tuning Code Language Models to Detect Cross-Language Bugs","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2510.21933","title":"A Comparison of Conversational Models and Humans in Answering Technical Questions: the Firefox Case","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2604.02398","title":"Improving MPI Error Detection and Repair with Large Language Models and Bug References","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.06723","title":"Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2609.07434","title":"CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.37216","title":"CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}