{"total":72,"rows":[{"id":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93,"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":"2404.14646","title":"Exploring and Unleashing the Power of Large Language Models in Automated Code Translation","created":"2024-04-23","cited_by_count":57,"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":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","cited_by_count":29,"area":null},{"id":"2504.11975","title":"SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes","created":"2025-04-16","cited_by_count":27,"area":null},{"id":"2502.00290","title":"Estimating LLM Uncertainty with Evidence","created":"2025-02-01","cited_by_count":26,"area":null},{"id":"2407.18276","title":"Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design","created":"2024-07-23","cited_by_count":24,"area":null},{"id":"2407.09726","title":"On Mitigating Code LLM Hallucinations with API Documentation","created":"2024-07-13","cited_by_count":21,"area":null},{"id":"2502.17898","title":"VeriPlan: Integrating Formal Verification and LLMs into End-User Planning","created":"2025-02-25","cited_by_count":20,"area":null},{"id":"2407.21424","title":"Cost-Effective Hallucination Detection for LLMs","created":"2024-07-31","cited_by_count":18,"area":null},{"id":"2405.02178","title":"Assessing and Verifying Task Utility in LLM-Powered Applications","created":"2024-05-03","cited_by_count":16,"area":null},{"id":"2512.23075","title":"Trust Region Masking for Long-Horizon LLM Reinforcement Learning","created":"2025-12-28","cited_by_count":16,"area":null},{"id":"2410.09997","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","created":"2024-10-13","cited_by_count":13,"area":null},{"id":"2502.17764","title":"DeepSeek vs. ChatGPT vs. Claude: A Comparative Study for Scientific Computing and Scientific Machine Learning Tasks","created":"2025-02-25","cited_by_count":12,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","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":"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":"2509.04292","title":"Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?","created":"2025-09-04","cited_by_count":10,"area":null},{"id":"2510.03029","title":"Investigating The Smells of LLM Generated Code","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2411.06493","title":"LProtector: An LLM-driven Vulnerability Detection System","created":"2024-11-10","cited_by_count":8,"area":null},{"id":"2412.12767","title":"A Survey of Calibration Process for Black-Box LLMs","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2504.18114","title":"Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection","created":"2025-04-25","cited_by_count":6,"area":null},{"id":"2406.07944","title":"Enhancing Differential Testing With LLMs For Testing Deep Learning Libraries","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2407.04831","title":"Code Hallucination","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2410.14748","title":"ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2504.13515","title":"Large Language Models for Validating Network Protocol Parsers","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2502.07036","title":"Automated Consistency Analysis of LLMs","created":"2025-02-10","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":"2507.11083","title":"Function-to-Style Guidance of LLMs for Code Translation","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2410.07820","title":"Mitigating Gender Bias in Code Large Language Models via Model Editing","created":"2024-10-10","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":"2410.12278","title":"Controlled Automatic Task-Specific Synthetic Data Generation for Hallucination Detection","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2410.14766","title":"Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarks","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2605.28500","title":"Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2409.15228","title":"A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2409.18395","title":"Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuning","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2410.15086","title":"Towards Safer Heuristics With XPlain","created":"2024-10-19","cited_by_count":2,"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":"2504.21276","title":"Assessing LLM code generation quality through path planning tasks","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2506.11021","title":"Eliminating Hallucination-Induced Errors in LLM Code Generation with Functional Clustering","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2510.23652","title":"The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2511.19355","title":"Leveraging LLMs for reward function design in reinforcement learning control tasks","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2602.18292","title":"Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers","created":"2026-02-20","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":"2608.23961","title":"Evaluating Language Models on Cross-Language Code Functional Equivalence","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2504.10167","title":"C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2505.09724","title":"An AI-Powered Research Assistant in the Lab: A Practical Guide for Text Analysis Through Iterative Collaboration with LLMs","created":"2025-05-14","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":"2601.03708","title":"MHRC-Bench: A Multilingual Hardware Repository-Level Code Completion benchmark","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2606.09800","title":"FASE: Fast Adaptive Semantic Entropy for Code Quality","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2609.13437","title":"LabAgent: Customize Any Research Hubs for Scientific Discoveries Using AI Agents","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2410.03904","title":"Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2503.05852","title":"Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2507.02057","title":"MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2508.09991","title":"Bridging AI Innovation and Healthcare Needs: Lessons Learned from Incorporating Modern NLP at The BC Cancer Registry","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2509.07676","title":"Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.25195","title":"Understanding Practitioners Perspectives on Monitoring Machine Learning Systems","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2510.24019","title":"Lifecycle-Aware code generation: Leveraging Software Engineering Phases in LLMs","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2511.16700","title":"RAG-Driven Data Quality Governance for Enterprise ERP Systems","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.04131","title":"Artificial Intelligence / Human Intelligence: Who Controls Whom?","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.14141","title":"TorchTraceAP: A New Benchmark Dataset for Detecting Performance Anti-Patterns in Computer Vision Models","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","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},{"id":"2605.24137","title":"Empirical Analysis and Detection of Hallucinations in LLM-Generated Bug Report Summaries","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.23107","title":"A Dual-Track Framework for Template-Constrained LaTeX Conversion","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.25402","title":"LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models","created":"2026-06-24","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":"2609.26480","title":"FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.05277","title":"Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.11300","title":"Characterizing Overconfident Failure in LLM-Based Code Generation","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}