{"total":19,"rows":[{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"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":"2408.08343","title":"API-guided Dataset Synthesis to Finetune Large Code Models","created":"2024-08-15","cited_by_count":11,"area":null},{"id":"2403.15230","title":"An Exploratory Investigation into Code License Infringements in Large Language Model Training Datasets","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2503.02296","title":"Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting","created":"2025-03-04","cited_by_count":7,"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":"2410.05797","title":"CodeCipher: Learning to Obfuscate Source Code Against LLMs","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2404.19432","title":"Can Large Language Models put 2 and 2 together? Probing for Entailed Arithmetical Relationships","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2507.01844","title":"Low-Perplexity LLM-Generated Sequences and Where To Find Them","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2510.16022","title":"Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization","created":"2025-10-15","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":"2503.22760","title":"Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2506.02791","title":"Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2507.17389","title":"Are AI Coders Snitches? An Empirical Study of Pretraining Data Detection on Code Large Language Models","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2508.16853","title":"DevLicOps: A Framework for Mitigating Licensing Risks in AI-Generated Code","created":"2025-08-23","cited_by_count":0,"area":null},{"id":"2512.11482","title":"Towards Privacy-Preserving Code Generation: Differentially Private Code Language Models","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2512.18456","title":"SoK: Understanding (New) Security Issues Across AI4Code Use Cases","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2604.21579","title":"A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2608.06640","title":"Characterizing the Quality Profile of AI-Generated C++ in Production","created":"2026-08-06","cited_by_count":0,"area":null}],"next_cursor":null}