{"total":192,"rows":[{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2407.00215","title":"LLM Critics Help Catch LLM Bugs","created":"2024-06-28","cited_by_count":147,"area":"lr"},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124,"area":"alignment"},{"id":"2302.07867","title":"Learning Performance-Improving Code Edits","created":"2023-02-15","cited_by_count":106,"area":null},{"id":"2307.09476","title":"Overthinking the Truth: Understanding how Language Models Process False Demonstrations","created":"2023-07-18","cited_by_count":81,"area":"lr"},{"id":"2412.16075","title":"Formal Mathematical Reasoning: A New Frontier in AI","created":"2024-12-20","cited_by_count":81,"area":"lr"},{"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":"2405.04760","title":"Large Language Models for Cyber Security: A Systematic Literature Review","created":"2024-05-08","cited_by_count":68,"area":null},{"id":"2310.17807","title":"Clover: Closed-Loop Verifiable Code Generation","created":"2023-10-26","cited_by_count":67,"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":"2212.10561","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","created":"2022-12-20","cited_by_count":64,"area":"lr"},{"id":"2301.02344","title":"TrojanPuzzle: Covertly Poisoning Code-Suggestion Models","created":"2023-01-06","cited_by_count":60,"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":"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":"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":"2306.10998","title":"RepoFusion: Training Code Models to Understand Your Repository","created":"2023-06-19","cited_by_count":40,"area":null},{"id":"2306.10073","title":"Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses","created":"2023-06-15","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":"2604.14228","title":"Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"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":"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":"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":"2601.18341","title":"Agentic Much? Adoption of Coding Agents on GitHub","created":"2026-01-26","cited_by_count":32,"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":"2303.12642","title":"Democratising AI: Multiple Meanings, Goals, and Methods","created":"2023-03-22","cited_by_count":29,"area":null},{"id":"2303.12961","title":"The Shaky Foundations of Clinical Foundation Models: A Survey of Large Language Models and Foundation Models for EMRs","created":"2023-03-22","cited_by_count":29,"area":null},{"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":"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":"2404.18353","title":"How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2406.01382","title":"Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function","created":"2024-06-03","cited_by_count":24,"area":null},{"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":"2401.17163","title":"Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chat","created":"2024-01-30","cited_by_count":23,"area":"agents"},{"id":"2404.14459","title":"LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitations","created":"2024-04-21","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":"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":"2304.14238","title":"The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who","created":"2023-04-27","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":"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":"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":"2503.22688","title":"CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation","created":"2025-03-05","cited_by_count":15,"area":null},{"id":"2509.22040","title":"\"Your AI, My Shell\": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors","created":"2025-09-26","cited_by_count":15,"area":"agents"},{"id":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2408.02509","title":"Black-Box Adversarial Attacks on LLM-Based Code Completion","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2412.14732","title":"Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Tools","created":"2024-12-19","cited_by_count":14,"area":null},{"id":"2402.05650","title":"Rocks Coding, Not Development--A Human-Centric, Experimental Evaluation of LLM-Supported SE Tasks","created":"2024-02-08","cited_by_count":13,"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":"2507.21928","title":"Vibe Coding as a Reconfiguration of Intent Mediation in Software Development: Definition, Implications, and Research Agenda","created":"2025-07-29","cited_by_count":13,"area":null},{"id":"2409.19182","title":"Artificial-Intelligence Generated Code Considered Harmful: A Road Map for Secure and High-Quality Code Generation","created":"2024-09-27","cited_by_count":12,"area":null},{"id":"2502.06039","title":"Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models","created":"2025-02-09","cited_by_count":12,"area":"lr"},{"id":"2404.03823","title":"An Investigation into Misuse of Java Security APIs by Large Language Models","created":"2024-04-04","cited_by_count":11,"area":null},{"id":"2407.08983","title":"Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2411.00932","title":"LLMs: A Game-Changer for Software Engineers?","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2512.04329","title":"A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks","created":"2025-12-03","cited_by_count":11,"area":"rag"},{"id":"2412.15004","title":"From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security","created":"2024-12-19","cited_by_count":10,"area":null},{"id":"2504.00018","title":"SandboxEval: Towards Securing Test Environment for Untrusted Code","created":"2025-03-27","cited_by_count":10,"area":null},{"id":"2506.11022","title":"Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox","created":"2025-05-19","cited_by_count":10,"area":null},{"id":"2312.14856","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code","created":"2023-12-22","cited_by_count":9,"area":null},{"id":"2403.03997","title":"Guiding Enumerative Program Synthesis with Large Language Models","created":"2024-03-06","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":"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":"2503.12511","title":"SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification","created":"2025-03-16","cited_by_count":9,"area":null},{"id":"2510.25015","title":"VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Verus","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2405.03616","title":"A Controlled Experiment on the Energy Efficiency of the Source Code Generated by Code Llama","created":"2024-05-06","cited_by_count":8,"area":null},{"id":"2507.13290","title":"Towards Formal Verification of LLM-Generated Code from Natural Language Prompts","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2504.20612","title":"The Hidden Risks of LLM-Generated Web Application Code: A Security-Centric Evaluation of Code Generation Capabilities in Large Language Models","created":"2025-04-29","cited_by_count":7,"area":null},{"id":"2601.21276","title":"More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests","created":"2026-01-29","cited_by_count":7,"area":"agents"},{"id":"2403.12671","title":"Enhancing Security of AI-Based Code Synthesis with GitHub Copilot via Cheap and Efficient Prompt-Engineering","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2509.24240","title":"Takedown: How It's Done in Modern Coding Agent Exploits","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2601.18345","title":"Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity","created":"2026-01-26","cited_by_count":6,"area":"agents"},{"id":"2407.11072","title":"MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants","created":"2024-07-12","cited_by_count":5,"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":"2501.16577","title":"Generative AI Uses and Risks for Knowledge Workers in a Science Organization","created":"2025-01-27","cited_by_count":5,"area":null},{"id":"2507.02976","title":"How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench","created":"2025-06-30","cited_by_count":5,"area":"agents"},{"id":"2508.00546","title":"SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval","created":"2025-08-01","cited_by_count":5,"area":null},{"id":"2601.13864","title":"HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation","created":"2026-01-20","cited_by_count":5,"area":null},{"id":"2312.09126","title":"Towards Trustworthy AI Software Development Assistance","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2501.11264","title":"Code Readability in the Age of Large Language Models: An Industrial Case Study from Atlassian","created":"2025-01-20","cited_by_count":4,"area":null},{"id":"2503.14281","title":"XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants","created":"2025-03-18","cited_by_count":4,"area":null},{"id":"2504.15284","title":"EditLord: Learning Code Transformation Rules for Code Editing","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2510.11195","title":"RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations","created":"2025-10-13","cited_by_count":4,"area":"rag"},{"id":"2512.18567","title":"AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software","created":"2025-12-21","cited_by_count":4,"area":null},{"id":"2601.01215","title":"Correctness isnt Efficiency: Runtime Memory Divergence in LLM-Generated Code","created":"2026-01-03","cited_by_count":4,"area":null},{"id":"2605.30777","title":"What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2404.09066","title":"CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistants","created":"2024-04-13","cited_by_count":3,"area":null},{"id":"2407.05202","title":"Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing","created":"2024-07-06","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":"2503.07770","title":"Evaluating LLaMA 3.2 for Software Vulnerability Detection","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2506.17347","title":"Distinguishing Task-Specific and General-Purpose AI in Regulation","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2510.22944","title":"Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2602.08915","title":"Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance","created":"2026-02-09","cited_by_count":3,"area":"agents"},{"id":"2603.17893","title":"scicode-lint: Detecting Methodology Bugs in Scientific Python Code with LLM-Generated Patterns","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2603.18740","title":"Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2605.04532","title":"Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap","created":"2026-05-06","cited_by_count":3,"area":null}],"next_cursor":"100"}