{"total":42,"rows":[{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498,"area":null},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359,"area":null},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170,"area":null},{"id":"2305.00418","title":"Using Large Language Models to Generate JUnit Tests: An Empirical Study","created":"2023-04-30","cited_by_count":53,"area":null},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49,"area":null},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"area":null},{"id":"2405.19782","title":"Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion","created":"2024-05-30","cited_by_count":40,"area":null},{"id":"2311.00889","title":"SALLM: Security Assessment of Generated Code","created":"2023-11-01","cited_by_count":39,"area":null},{"id":"2402.16197","title":"Language Models for Code Completion: A Practical Evaluation","created":"2024-02-25","cited_by_count":39,"area":null},{"id":"2310.16263","title":"Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation","created":"2023-10-25","cited_by_count":15,"area":null},{"id":"2307.08220","title":"FRANC: A Lightweight Framework for High-Quality Code Generation","created":"2023-07-17","cited_by_count":14,"area":null},{"id":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2410.04490","title":"A Large-Scale Exploit Instrumentation Study of AI/ML Supply Chain Attacks in Hugging Face Models","created":"2024-10-06","cited_by_count":14,"area":null},{"id":"2408.11710","title":"Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests","created":"2024-08-21","cited_by_count":11,"area":null},{"id":"2211.04673","title":"Syntax-Aware On-the-Fly Code Completion","created":"2022-11-09","cited_by_count":10,"area":null},{"id":"2302.13681","title":"The (ab)use of Open Source Code to Train Large Language Models","created":"2023-02-27","cited_by_count":10,"area":null},{"id":"2409.15204","title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","created":"2024-09-23","cited_by_count":10,"area":null},{"id":"2205.10692","title":"All You Need Is Logs: Improving Code Completion by Learning from Anonymous IDE Usage Logs","created":"2022-05-21","cited_by_count":9,"area":null},{"id":"2404.10155","title":"The Fault in our Stars: Quality Assessment of Code Generation Benchmarks","created":"2024-04-15","cited_by_count":9,"area":null},{"id":"2304.12269","title":"Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2403.15185","title":"Investigating the Performance of Language Models for Completing Code in Functional Programming Languages: a Haskell Case Study","created":"2024-03-22","cited_by_count":7,"area":null},{"id":"2206.14578","title":"Evaluating Generative Patent Language Models","created":"2022-06-23","cited_by_count":6,"area":null},{"id":"2305.17145","title":"Type Prediction With Program Decomposition and Fill-in-the-Type Training","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2504.01850","title":"Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming Tasks","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2302.13149","title":"STACC: Code Comment Classification using SentenceTransformers","created":"2023-02-25","cited_by_count":5,"area":null},{"id":"2405.14753","title":"A Transformer-Based Approach for Smart Invocation of Automatic Code Completion","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2308.13354","title":"On the Impact of Language Selection for Training and Evaluating Programming Language Models","created":"2023-08-25","cited_by_count":4,"area":null},{"id":"2210.02853","title":"NeuDep: Neural Binary Memory Dependence Analysis","created":"2022-10-04","cited_by_count":3,"area":null},{"id":"2306.06620","title":"ARIST: An Effective API Argument Recommendation Approach","created":"2023-06-11","cited_by_count":2,"area":null},{"id":"2501.02491","title":"Rethinking IDE Customization for Enhanced HAX: A Hyperdimensional Perspective","created":"2025-01-05","cited_by_count":2,"area":null},{"id":"2504.09474","title":"MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2505.15469","title":"A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2604.27296","title":"To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2211.00381","title":"An Empirical Study on Data Leakage and Generalizability of Link Prediction Models for Issues and Commits","created":"2022-11-01","cited_by_count":1,"area":null},{"id":"2406.10141","title":"The Rise and Fall(?) of Software Engineering","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2601.10496","title":"Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2405.06835","title":"Automating Code Adaptation for MLOps -- A Benchmarking Study on LLMs","created":"2024-05-10","cited_by_count":0,"area":null},{"id":"2508.02455","title":"TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2509.12395","title":"Evaluating Large Language Models for Functional and Maintainable Code in Industrial Settings: A Case Study at ASML","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2510.04349","title":"Challenge on Optimization of Context Collection for Code Completion","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2512.21238","title":"Assessing the Software Security Comprehension of Large Language Models","created":"2025-12-24","cited_by_count":0,"area":null}],"next_cursor":null}