{"total":28,"rows":[{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2405.00253","title":"CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification","created":"2024-04-30","cited_by_count":34,"area":null},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"area":null},{"id":"2406.13890","title":"ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World","created":"2024-06-19","cited_by_count":28,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","cited_by_count":26,"area":null},{"id":"2412.17744","title":"RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation","created":"2024-12-23","cited_by_count":23,"area":null},{"id":"2410.01353","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2505.16667","title":"ELABORATION: A Comprehensive Benchmark on Human-LLM Competitive Programming","created":"2025-05-22","cited_by_count":16,"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":"2312.10321","title":"LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2407.11470","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2505.10494","title":"Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective","created":"2025-05-15","cited_by_count":6,"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":"2507.11083","title":"Function-to-Style Guidance of LLMs for Code Translation","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2508.07180","title":"Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2509.14899","title":"CARGO: A Framework for Confidence-Aware Routing of Large Language Models","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2603.10846","title":"Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis","created":"2026-03-11","cited_by_count":3,"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":"2502.02866","title":"A Systematic Approach for Assessing Large Language Models' Test Case Generation Capability","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2504.03541","title":"Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsing","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2504.20673","title":"CoCo-Bench: A Comprehensive Code Benchmark For Multi-task Large Language Model Evaluation","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2601.04540","title":"AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.06565","title":"EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2512.18456","title":"SoK: Understanding (New) Security Issues Across AI4Code Use Cases","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2603.09978","title":"One Model, Many Skills: Parameter-Efficient Fine-Tuning for Multitask Code Analysis","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2609.33192","title":"AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}