{"total":46,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93,"area":null},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2401.16186","title":"An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project","created":"2024-01-29","cited_by_count":28,"area":null},{"id":"2503.17502","title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","created":"2025-03-21","cited_by_count":16,"area":null},{"id":"2407.00456","title":"Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models","created":"2024-06-29","cited_by_count":15,"area":null},{"id":"2403.15600","title":"Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers","created":"2024-03-22","cited_by_count":13,"area":null},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2510.25506","title":"Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies","created":"2025-10-29","cited_by_count":12,"area":null},{"id":"2507.20439","title":"When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions","created":"2025-07-27","cited_by_count":11,"area":null},{"id":"2401.08376","title":"KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation","created":"2024-01-16","cited_by_count":10,"area":null},{"id":"2407.11470","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2410.23074","title":"Multi-Programming Language Sandbox for LLMs","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2503.16922","title":"RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10,"area":null},{"id":"2502.14202","title":"Do LLMs Consider Security? An Empirical Study on Responses to Programming Questions","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2310.01727","title":"Can GPT-4 Replicate Empirical Software Engineering Research?","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2509.10099","title":"Generating Energy-Efficient Code via Large-Language Models -- Where are we now?","created":"2025-09-12","cited_by_count":6,"area":null},{"id":"2312.15614","title":"A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2602.11083","title":"Token-Efficient Change Detection in LLM APIs","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2403.06485","title":"Knowledge-aware Alert Aggregation in Large-scale Cloud Systems: a Hybrid Approach","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2507.21285","title":"Curiosity by Design: An LLM-based Coding Assistant Asking Clarification Questions","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2509.25242","title":"A Benchmark for Localizing Code and Non-Code Issues in Software Projects","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2510.21192","title":"Gen-Review: A Large-scale Dataset of AI-Generated (and Human-written) Peer Reviews","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2606.31511","title":"Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2409.16559","title":"Demystifying Issues, Causes and Solutions in LLM Open-Source Projects","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2503.07556","title":"Novice Developers' Perspectives on Adopting LLMs for Software Development: A Systematic Literature Review","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2404.09249","title":"Test Code Generation for Telecom Software Systems using Two-Stage Generative Model","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2409.06416","title":"Exploring the Integration of Large Language Models in Industrial Test Maintenance Processes","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2506.16440","title":"Evaluating the Use of LLMs for Documentation to Code Traceability","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2509.25043","title":"Large Language Models for Software Testing: A Research Roadmap","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2407.12830","title":"Knowledge-based Consistency Testing of Large Language Models","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2412.19088","title":"Integrating Artificial Open Generative Artificial Intelligence into Software Supply Chain Security","created":"2024-12-26","cited_by_count":1,"area":null},{"id":"2508.02773","title":"Web3 x AI Agents: Landscape, Integrations, and Foundational Challenges","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2509.05716","title":"A Survey of the State-of-the-Art in Conversational Question Answering Systems","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2602.17697","title":"Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.19504","title":"Beyond the Desk: Barriers and Future Opportunities for AI to Assist Scientists in Embodied Physical Tasks","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2607.03174","title":"Effectiveness of LLM-based Software Diversity for Reliability Improvement -- an Empirical Study","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2505.18019","title":"LLM assisted web application functional requirements generation: A case study of four popular LLMs over a Mess Management System","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2511.01316","title":"Exploringand Unleashing the Power of Large Language Models in CI/CD Configuration Translation","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2604.06946","title":"An empirical study of LoRA-based fine-tuning of large language models for automated test case generation","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.25536","title":"A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.28307","title":"From Textual Requirements to Microservice Architectures - A Comprehensive Evaluation of LLM-Based Design Synthesis","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.27442","title":"From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01601","title":"Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}