{"total":45,"rows":[{"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":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107,"area":null},{"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":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2406.19783","title":"NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations","created":"2024-06-28","cited_by_count":20,"area":null},{"id":"2503.17181","title":"A Study of LLMs' Preferences for Libraries and Programming Languages","created":"2025-03-21","cited_by_count":20,"area":null},{"id":"2404.03398","title":"Scaling Up Video Summarization Pretraining with Large Language Models","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2310.04963","title":"LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation","created":"2023-10-08","cited_by_count":15,"area":null},{"id":"2505.24138","title":"AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuits","created":"2025-05-30","cited_by_count":15,"area":null},{"id":"2310.19181","title":"From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude","created":"2023-10-29","cited_by_count":13,"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":"2310.05318","title":"Resolving the Imbalance Issue in Hierarchical Disciplinary Topic Inference via LLM-based Data Augmentation","created":"2023-10-09","cited_by_count":11,"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":"2505.18098","title":"Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2502.08108","title":"Generative AI and Empirical Software Engineering: A Paradigm Shift","created":"2025-02-12","cited_by_count":9,"area":null},{"id":"2401.06628","title":"OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models","created":"2024-01-12","cited_by_count":8,"area":null},{"id":"2601.21448","title":"ChipBench: A Next-Step Benchmark for Evaluating LLM Performance in AI-Aided Chip Design","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2408.05128","title":"Is ChatGPT a Good Software Librarian? An Exploratory Study on the Use of ChatGPT for Software Library Recommendations","created":"2024-08-09","cited_by_count":7,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2506.12355","title":"QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm","created":"2025-06-14","cited_by_count":4,"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":"2408.06423","title":"Evaluating LLMs on Entity Disambiguation in Tables","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2507.10818","title":"How Robust are LLM-Generated Library Imports? An Empirical Study using Stack Overflow","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2508.13092","title":"VerilogLAVD: LLM-Aided Rule Generation for Vulnerability Detection in Verilog","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2402.07913","title":"QACP: An Annotated Question Answering Dataset for Assisting Chinese Python Programming Learners","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2504.16116","title":"DMind Benchmark: Toward a Holistic Assessment of LLM Capabilities across the Web3 Domain","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2506.18952","title":"LLMs on a Budget? Say HOLA","created":"2025-06-23","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":"2509.22202","title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.04548","title":"Learning Linear Regression with Low-Rank Tasks in-Context","created":"2025-10-06","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":"2605.13280","title":"Characterizing Readability Issue Patterns and the Role of Prompt Design in LLM-Generated Code","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2402.00689","title":"Ocassionally Secure: A Comparative Analysis of Code Generation Assistants","created":"2024-02-01","cited_by_count":0,"area":null},{"id":"2404.14680","title":"Automated Multi-Language to English Machine Translation Using Generative Pre-Trained Transformers","created":"2024-04-23","cited_by_count":0,"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":"2510.15494","title":"Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.04538","title":"From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2602.08085","title":"Large language models for spreading dynamics in complex systems","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2603.11212","title":"Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.14867","title":"Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2608.11513","title":"Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.14565","title":"Position: AI Lock-In Is in Progress, and We Must Be Prepared","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2610.15482","title":"Security in LLM-Assisted Coding: A Systematic Literature Review","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}