{"total":53,"rows":[{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107,"area":null},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2504.09246","title":"Type-Constrained Code Generation with Language Models","created":"2025-04-12","cited_by_count":35,"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":"2411.02310","title":"MdEval: Massively Multilingual Code Debugging","created":"2024-11-04","cited_by_count":16,"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":"2404.10225","title":"Rethinking Software Engineering in the Foundation Model Era: From Task-Driven AI Copilots to Goal-Driven AI Pair Programmers","created":"2024-04-16","cited_by_count":12,"area":null},{"id":"2504.20799","title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","created":"2025-04-29","cited_by_count":11,"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":"2411.01414","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2411.06638","title":"Model Editing for LLMs4Code: How Far are We?","created":"2024-11-11","cited_by_count":10,"area":null},{"id":"2510.26130","title":"Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2505.16170","title":"When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction","created":"2025-05-22","cited_by_count":6,"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":"2408.13372","title":"Understanding Defects in Generated Codes by Language Models","created":"2024-08-23","cited_by_count":5,"area":null},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2504.04372","title":"Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models","created":"2025-04-06","cited_by_count":4,"area":null},{"id":"2504.12608","title":"Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2405.13932","title":"Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2407.21227","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2410.09268","title":"One Step at a Time: Combining LLMs and Static Analysis to Generate Next-Step Hints for Programming Tasks","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2502.18726","title":"Deep-Bench: Deep Learning Benchmark Dataset for Code Generation","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2411.13269","title":"Towards Specification-Driven LLM-Based Generation of Embedded Automotive Software","created":"2024-11-20","cited_by_count":2,"area":null},{"id":"2504.21276","title":"Assessing LLM code generation quality through path planning tasks","created":"2025-04-30","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":"2505.18220","title":"Navigating Pitfalls: Evaluating LLMs in Machine Learning Programming Education","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2512.08810","title":"Multicalibration for LLM-based Code Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2604.17338","title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2607.01867","title":"An Exploratory Study on LLM-Generated Code and Comments in Code Repositories","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2407.08890","title":"DeepCodeProbe: Towards Understanding What Models Trained on Code Learn","created":"2024-07-11","cited_by_count":1,"area":null},{"id":"2504.16485","title":"On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2507.16203","title":"SVAgent: AI Agent for Hardware Security Verification Assertion","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2509.20277","title":"Investigating Security Implications of Automatically Generated Code on the Software Supply Chain","created":"2025-09-24","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":"2605.05267","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2607.03174","title":"Effectiveness of LLM-based Software Diversity for Reliability Improvement -- an Empirical Study","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2506.12014","title":"code_transformed: The Influence of Large Language Models on Code","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2507.19390","title":"ReCatcher: Towards LLMs Regression Testing for Code Generation","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2509.10946","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2509.20172","title":"Benchmarking Web API Integration Code Generation","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.10216","title":"Learning to Guarantee Type Correctness in Code Generation through Type-Guided Program Synthesis","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2601.18949","title":"Tricky$^2$: Towards a Benchmark for Evaluating Human and LLM Error Interactions","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2604.19826","title":"Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.23361","title":"An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2606.12620","title":"HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.14113","title":"Simulating Students' Java Programming Errors with Large Language Models","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.02057","title":"Prompt Coverage Adequacy","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.10187","title":"Knowledge-Conditioned, Single-Pass LLM Synthesis of Executable Unity Game Scenes: A Compiler Error Census across 26 Goal Playable Concepts","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.22652","title":"Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated Code","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.09135","title":"Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.12708","title":"What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}