{"total":431,"rows":[{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004,"area":"lr"},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799,"area":null},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619,"area":null},{"id":"2308.00708","title":"VeriGen: A Large Language Model for Verilog Code Generation","created":"2023-07-28","cited_by_count":200,"area":null},{"id":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155,"area":null},{"id":"2206.15331","title":"GitHub Copilot AI pair programmer: Asset or Liability?","created":"2022-06-30","cited_by_count":152,"area":null},{"id":"2305.15060","title":"Who Wrote this Code? Watermarking for Code Generation","created":"2023-05-24","cited_by_count":141,"area":"safety"},{"id":"2305.13243","title":"Chip-Chat: Challenges and Opportunities in Conversational Hardware Design","created":"2023-05-22","cited_by_count":140,"area":null},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138,"area":null},{"id":"2312.04724","title":"Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models","created":"2023-12-07","cited_by_count":138,"area":null},{"id":"2212.11140","title":"Benchmarking Large Language Models for Automated Verilog RTL Code Generation","created":"2022-12-13","cited_by_count":115,"area":null},{"id":"2212.01020","title":"Programming Is Hard -- Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generation","created":"2022-12-02","cited_by_count":99,"area":null},{"id":"2406.05590","title":"NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security","created":"2024-06-08","cited_by_count":93,"area":null},{"id":"2210.14306","title":"Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming","created":"2022-10-25","cited_by_count":91,"area":null},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91,"area":null},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91,"area":null},{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90,"area":"agents"},{"id":"2412.16075","title":"Formal Mathematical Reasoning: A New Frontier in AI","created":"2024-12-20","cited_by_count":81,"area":"lr"},{"id":"2402.18649","title":"A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems","created":"2024-02-28","cited_by_count":77,"area":null},{"id":"2308.10335","title":"Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation","created":"2023-08-20","cited_by_count":73,"area":null},{"id":"2408.02232","title":"SpecRover: Code Intent Extraction via LLMs","created":"2024-08-05","cited_by_count":72,"area":"agents"},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2402.09497","title":"Instruction Tuning for Secure Code Generation","created":"2024-02-14","cited_by_count":68,"area":null},{"id":"2210.11630","title":"Using Large Language Models to Enhance Programming Error Messages","created":"2022-10-20","cited_by_count":67,"area":null},{"id":"2310.17807","title":"Clover: Closed-Loop Verifiable Code Generation","created":"2023-10-26","cited_by_count":67,"area":null},{"id":"2303.07839","title":"ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design","created":"2023-03-11","cited_by_count":66,"area":null},{"id":"2406.10279","title":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","created":"2024-06-12","cited_by_count":65,"area":null},{"id":"2304.02491","title":"\"It's Weird That it Knows What I Want\": Usability and Interactions with Copilot for Novice Programmers","created":"2023-04-05","cited_by_count":64,"area":null},{"id":"2303.09384","title":"LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations","created":"2023-03-16","cited_by_count":62,"area":null},{"id":"2301.02344","title":"TrojanPuzzle: Covertly Poisoning Code-Suggestion Models","created":"2023-01-06","cited_by_count":60,"area":null},{"id":"2501.08200","title":"CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation","created":"2025-01-14","cited_by_count":59,"area":null},{"id":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58,"area":"safety"},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2302.04012","title":"CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models","created":"2023-02-08","cited_by_count":55,"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":"2306.02608","title":"Computing Education in the Era of Generative AI","created":"2023-06-05","cited_by_count":52,"area":null},{"id":"2401.12970","title":"Raidar: geneRative AI Detection viA Rewriting","created":"2024-01-23","cited_by_count":52,"area":null},{"id":"2402.16965","title":"WIPI: A New Web Threat for LLM-Driven Web Agents","created":"2024-02-26","cited_by_count":51,"area":"agents"},{"id":"2407.21579","title":"A Performance Study of LLM-Generated Code on Leetcode","created":"2024-07-31","cited_by_count":49,"area":null},{"id":"2303.11455","title":"Large Language Models and Simple, Stupid Bugs","created":"2023-03-20","cited_by_count":45,"area":null},{"id":"2406.07765","title":"Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward","created":"2024-06-11","cited_by_count":45,"area":null},{"id":"2604.20779","title":"SWE-chat: Coding Agent Interactions From Real Users in the Wild","created":"2026-04-22","cited_by_count":43,"area":"agents"},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2208.06213","title":"What is it like to program with artificial intelligence?","created":"2022-08-12","cited_by_count":39,"area":null},{"id":"2311.00889","title":"SALLM: Security Assessment of Generated Code","created":"2023-11-01","cited_by_count":39,"area":null},{"id":"2304.08979","title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","created":"2023-04-18","cited_by_count":37,"area":null},{"id":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37,"area":null},{"id":"2405.00218","title":"Constrained Decoding for Secure Code Generation","created":"2024-04-30","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":"2409.10737","title":"AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing","created":"2024-09-16","cited_by_count":35,"area":"agents"},{"id":"2412.06176","title":"AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement","created":"2024-12-09","cited_by_count":35,"area":"synth"},{"id":"2504.09246","title":"Type-Constrained Code Generation with Language Models","created":"2025-04-12","cited_by_count":35,"area":null},{"id":"2307.02192","title":"The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification","created":"2023-07-05","cited_by_count":34,"area":null},{"id":"2407.07064","title":"Prompting Techniques for Secure Code Generation: A Systematic Investigation","created":"2024-07-09","cited_by_count":34,"area":null},{"id":"2505.23135","title":"VERINA: Benchmarking Verifiable Code Generation","created":"2025-05-29","cited_by_count":34,"area":null},{"id":"2308.04451","title":"Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks","created":"2023-08-04","cited_by_count":33,"area":"safety"},{"id":"2312.04730","title":"DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructions","created":"2023-12-07","cited_by_count":33,"area":null},{"id":"2306.04556","title":"StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Code","created":"2023-06-07","cited_by_count":32,"area":null},{"id":"2306.14027","title":"(Security) Assertions by Large Language Models","created":"2023-06-24","cited_by_count":32,"area":null},{"id":"2307.02503","title":"Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review","created":"2023-07-04","cited_by_count":32,"area":null},{"id":"2304.10423","title":"Fully Autonomous Programming with Large Language Models","created":"2023-04-20","cited_by_count":31,"area":null},{"id":"2306.13906","title":"Can GPT-4 Support Analysis of Textual Data in Tasks Requiring Highly Specialized Domain Expertise?","created":"2023-06-24","cited_by_count":31,"area":null},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"area":"agents"},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"area":null},{"id":"2311.11690","title":"Refactoring Programs Using Large Language Models with Few-Shot Examples","created":"2023-11-20","cited_by_count":28,"area":null},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2407.02395","title":"Toward Secure Code Generation: Bridging Correctness and Security via Task-Adaptive Vulnerability Modeling and Execution-Based Benchmarking","created":"2024-07-02","cited_by_count":27,"area":null},{"id":"2401.15963","title":"NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness","created":"2024-01-29","cited_by_count":26,"area":null},{"id":"2411.12882","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","created":"2024-11-19","cited_by_count":25,"area":"alignment"},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2511.04427","title":"Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects","created":"2025-11-06","cited_by_count":24,"area":"agents"},{"id":"2401.00788","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","created":"2024-01-01","cited_by_count":23,"area":null},{"id":"2406.07737","title":"The Future of AI-Driven Software Engineering","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2306.15121","title":"Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation","created":"2023-06-27","cited_by_count":22,"area":null},{"id":"2407.02209","title":"Generative Monoculture in Large Language Models","created":"2024-07-02","cited_by_count":22,"area":null},{"id":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2310.02368","title":"Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation","created":"2023-10-03","cited_by_count":21,"area":"alignment"},{"id":"2407.09726","title":"On Mitigating Code LLM Hallucinations with API Documentation","created":"2024-07-13","cited_by_count":21,"area":null},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2302.07248","title":"Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions","created":"2023-02-14","cited_by_count":20,"area":null},{"id":"2306.05153","title":"Is AI the better programming partner? Human-Human Pair Programming vs. Human-AI pAIr Programming","created":"2023-06-08","cited_by_count":20,"area":null},{"id":"2405.01787","title":"Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming","created":"2024-05-03","cited_by_count":20,"area":null},{"id":"2508.20816","title":"Multi-Agent Penetration Testing AI for the Web","created":"2025-08-28","cited_by_count":20,"area":"agents"},{"id":"2309.04142","title":"Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2409.12699","title":"PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)","created":"2024-09-19","cited_by_count":19,"area":null},{"id":"2502.01853","title":"Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysis","created":"2025-02-03","cited_by_count":19,"area":null},{"id":"2506.05692","title":"SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code","created":"2025-06-06","cited_by_count":19,"area":null},{"id":"2406.17910","title":"Transforming Software Development: Evaluating the Efficiency and Challenges of GitHub Copilot in Real-World Projects","created":"2024-06-25","cited_by_count":18,"area":null},{"id":"2410.12468","title":"Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios","created":"2024-10-16","cited_by_count":18,"area":"agents"},{"id":"2304.12512","title":"Semantic Compression With Large Language Models","created":"2023-04-25","cited_by_count":17,"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":"2602.09185","title":"AIDev: Studying AI Coding Agents on GitHub","created":"2026-02-09","cited_by_count":17,"area":"agents"},{"id":"2302.04030","title":"CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models","created":"2023-02-08","cited_by_count":16,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2401.03374","title":"LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward","created":"2024-01-07","cited_by_count":16,"area":null},{"id":"2408.11006","title":"Security Attacks on LLM-based Code Completion Tools","created":"2024-08-20","cited_by_count":16,"area":"safety"},{"id":"2409.06446","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","created":"2024-09-10","cited_by_count":16,"area":null},{"id":"2504.16429","title":"Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection","created":"2025-04-23","cited_by_count":16,"area":"rag"},{"id":"2310.06680","title":"Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach","created":"2023-10-10","cited_by_count":15,"area":null}],"next_cursor":"100"}