{"total":24,"rows":[{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391,"area":null},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35,"area":null},{"id":"2404.00566","title":"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks","created":"2024-03-31","cited_by_count":23,"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":"2405.04520","title":"NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts","created":"2024-05-07","cited_by_count":19,"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":"2409.10741","title":"NaviQAte: Functionality-Guided Web Application Navigation","created":"2024-09-16","cited_by_count":9,"area":null},{"id":"2505.10593","title":"LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps","created":"2025-05-15","cited_by_count":8,"area":null},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","cited_by_count":6,"area":null},{"id":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2312.04687","title":"LLM4TDD: Best Practices for Test Driven Development Using Large Language Models","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2401.08138","title":"LLMs for Test Input Generation for Semantic Caches","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2401.17626","title":"Generative AI to Generate Test Data Generators","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2409.06416","title":"Exploring the Integration of Large Language Models in Industrial Test Maintenance Processes","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2503.23231","title":"CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2509.25043","title":"Large Language Models for Software Testing: A Research Roadmap","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2504.17203","title":"High-Fidelity And Complex Test Data Generation For Google SQL Code Generation Services","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2404.01240","title":"AURORA: Navigating UI Tarpits via Automated Neural Screen Understanding","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2407.02791","title":"Model-Enhanced LLM-Driven VUI Testing of VPA Apps","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2503.05102","title":"AutoTestForge: A Multidimensional Automated Testing Framework for Natural Language Processing Models","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2607.28750","title":"DragonCrawl: A Generative, Intent-Based Framework for Scalable Mobile End-to-End Testing","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.25425","title":"RotDroid: Cross-Orientation State Equivalence Testing for Detecting GUI Rotation Bugs in Android Apps","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}