{"total":37,"rows":[{"id":"2402.15938","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","created":"2024-02-24","cited_by_count":122,"area":null},{"id":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70,"area":null},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57,"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":"2510.18471","title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","created":"2025-10-21","cited_by_count":24,"area":null},{"id":"2508.19764","title":"Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance","created":"2025-08-27","cited_by_count":18,"area":null},{"id":"2307.08220","title":"FRANC: A Lightweight Framework for High-Quality Code Generation","created":"2023-07-17","cited_by_count":14,"area":null},{"id":"2408.11081","title":"What can Large Language Models Capture about Code Functional Equivalence?","created":"2024-08-20","cited_by_count":14,"area":null},{"id":"2506.10948","title":"Execution Guided Line-by-Line Code Generation","created":"2025-06-12","cited_by_count":10,"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":"2502.02928","title":"Large Language Model Guided Self-Debugging Code Generation","created":"2025-02-05","cited_by_count":8,"area":null},{"id":"2406.06559","title":"Harnessing Business and Media Insights with Large Language Models","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2411.14503","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","created":"2024-11-21","cited_by_count":7,"area":null},{"id":"2307.00012","title":"FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair","created":"2023-06-21","cited_by_count":6,"area":null},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2503.22851","title":"RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2506.10337","title":"GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2408.13745","title":"DOCE: Finding the Sweet Spot for Execution-Based Code Generation","created":"2024-08-25","cited_by_count":4,"area":null},{"id":"2408.15630","title":"CodeSift: An LLM-Based Reference-Less Framework for Automatic Code Validation","created":"2024-08-28","cited_by_count":4,"area":null},{"id":"2410.11096","title":"SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI","created":"2024-10-14","cited_by_count":4,"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":"2505.15356","title":"NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2507.12284","title":"MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks","created":"2025-07-16","cited_by_count":4,"area":null},{"id":"2510.03178","title":"When Names Disappear: Revealing What LLMs Actually Understand About Code","created":"2025-10-03","cited_by_count":4,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2403.00046","title":"Exploring Data-Efficient Adaptation of Large Language Models for Code Generation","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2602.07080","title":"CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2403.10575","title":"Exploring Language Model's Code Generation Ability with Auxiliary Functions","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2607.11358","title":"RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2407.14530","title":"FuncEvalGMN: Evaluating Functional Correctness of SQL via Graph Matching Network","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2510.23169","title":"MATCH: Task-Driven Code Evaluation through Contrastive Learning","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2608.29696","title":"Ideation Arena: Evaluating LLM Generated Research Ideas with Battle-style Human Expert Assessment","created":"2026-08-30","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":"2601.14528","title":"LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2604.13946","title":"CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.27780","title":"RuC: HDL-Agnostic Rule Completion Benchmark Generation","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2610.13811","title":"QTestBench: A Test Framework for Evaluating LLM-Generated Quantum Code","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}