{"total":18,"rows":[{"id":"2503.01245","title":"Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2501.12934","title":"Correctness Assessment of Code Generated by Large Language Models Using Internal Representations","created":"2025-01-22","cited_by_count":17,"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":"2503.10784","title":"Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview","created":"2025-03-13","cited_by_count":7,"area":null},{"id":"2506.11059","title":"CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2412.16594","title":"AIGCodeSet: A New Annotated Dataset for AI Generated Code Detection","created":"2024-12-21","cited_by_count":5,"area":null},{"id":"2503.19217","title":"LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languages","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2508.01371","title":"Prompt to Pwn: Automated Exploit Generation for Smart Contracts","created":"2025-08-02","cited_by_count":4,"area":null},{"id":"2502.18468","title":"SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2507.21693","title":"MultiAIGCD: A Comprehensive dataset for AI Generated Code Detection Covering Multiple Languages, Models,Prompts, and Scenarios","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2409.01382","title":"Automatic Detection of LLM-Generated Code: A Comparative Case Study of Contemporary Models Across Function and Class Granularities","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2505.03818","title":"Program Semantic Inequivalence Game with Large Language Models","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2505.23598","title":"LLM Performance for Code Generation on Noisy Tasks","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2511.03898","title":"Secure Code Generation at Scale with Reflexion","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2602.04894","title":"Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2509.13650","title":"GitHub's Copilot Code Review: Can AI Spot Security Flaws Before You Commit?","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2604.12311","title":"Is Vibe Coding the Future? An Empirical Assessment of LLM Generated Codes for Construction Safety","created":"2026-04-14","cited_by_count":0,"area":null}],"next_cursor":null}