{"total":61,"rows":[{"id":"2410.15037","title":"mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation","created":"2024-10-19","cited_by_count":32,"area":null},{"id":"2411.09116","title":"P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs","created":"2024-11-14","cited_by_count":29,"area":null},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23,"area":null},{"id":"2406.11687","title":"Tokenization Falling Short: On Subword Robustness in Large Language Models","created":"2024-06-17","cited_by_count":20,"area":null},{"id":"2412.11990","title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","created":"2024-12-16","cited_by_count":20,"area":null},{"id":"2506.13832","title":"FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation","created":"2025-06-16","cited_by_count":20,"area":null},{"id":"2509.22908","title":"A benchmark for vericoding: formally verified program synthesis","created":"2025-09-26","cited_by_count":20,"area":null},{"id":"2406.03777","title":"Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices","created":"2024-06-06","cited_by_count":17,"area":null},{"id":"2503.06689","title":"DependEval: Benchmarking LLMs for Repository Dependency Understanding","created":"2025-03-09","cited_by_count":17,"area":null},{"id":"2411.01063","title":"InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation","created":"2024-11-01","cited_by_count":16,"area":null},{"id":"2411.02310","title":"MdEval: Massively Multilingual Code Debugging","created":"2024-11-04","cited_by_count":16,"area":null},{"id":"2410.01079","title":"Concept Space Alignment in Multilingual LLMs","created":"2024-10-01","cited_by_count":13,"area":null},{"id":"2411.00932","title":"LLMs: A Game-Changer for Software Engineers?","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2404.00399","title":"Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code","created":"2024-03-30","cited_by_count":10,"area":null},{"id":"2507.18791","title":"CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages","created":"2025-07-24","cited_by_count":10,"area":null},{"id":"2409.15890","title":"HLB: Benchmarking LLMs' Humanlikeness in Language Use","created":"2024-09-24","cited_by_count":8,"area":null},{"id":"2506.02073","title":"Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2512.00020","title":"Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead","created":"2025-10-29","cited_by_count":8,"area":null},{"id":"2510.10238","title":"The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities","created":"2025-10-11","cited_by_count":7,"area":null},{"id":"2601.17858","title":"MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging","created":"2026-01-25","cited_by_count":7,"area":null},{"id":"2406.03636","title":"Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages","created":"2024-06-05","cited_by_count":6,"area":null},{"id":"2505.12331","title":"OSS-Bench: Benchmark Generator for Coding LLMs","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2507.15850","title":"3LM: Bridging Arabic, STEM, and Code through Benchmarking","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2410.17736","title":"MojoBench: Language Modeling and Benchmarks for Mojo","created":"2024-10-23","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":"2508.03678","title":"More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2510.07740","title":"AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2409.04114","title":"Multi-Programming Language Ensemble for Code Generation in Large Language Model","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2410.16292","title":"An evaluation of LLM code generation capabilities through graded exercises","created":"2024-10-06","cited_by_count":3,"area":null},{"id":"2412.08291","title":"Code LLMs: A Taxonomy-based Survey","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2512.14018","title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2604.16625","title":"AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2408.11431","title":"Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2502.17253","title":"MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2505.11441","title":"Is Compression Really Linear with Code Intelligence?","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2508.17948","title":"Debiasing Multilingual LLMs in Cross-lingual Latent Space","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2510.21193","title":"Estonian Native Large Language Model Benchmark","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2604.14210","title":"Chinese Language Is Not More Efficient Than English in Vibe Coding: A Preliminary Study on Token Cost and Problem-Solving Rate","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2604.25960","title":"Large Language Models for Multilingual Code Intelligence: A Survey","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2606.20517","title":"Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2404.14419","title":"Evaluation and Improvement of Fault Detection for Large Language Models","created":"2024-04-14","cited_by_count":1,"area":null},{"id":"2408.09701","title":"Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2502.19067","title":"IndicEval-XL: Bridging Linguistic Diversity in Code Generation Across Indic Languages","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2505.20505","title":"Large Language Models for IT Automation Tasks: Are We There Yet?","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2601.02060","title":"Perish or Flourish? A Holistic Evaluation of Large Language Models for Code Generation in Functional Programming","created":"2026-01-05","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":"2609.32248","title":"Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2405.07495","title":"MacBehaviour: An R package for behavioural experimentation on large language models","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2505.24324","title":"SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.19904","title":"CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2510.09898","title":"Learning Bug Context for PyTorch-to-JAX Translation with LLMs","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.11281","title":"PADME: Procedure Aware DynaMic Execution","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.12487","title":"Diff-XYZ: A Benchmark for Evaluating Diff Understanding","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.13163","title":"A Matter of Representation: Towards Graph-Based Abstract Code Generation","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2603.14501","title":"CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2604.06253","title":"FLeX: Fourier-based Low-rank EXpansion for multilingual transfer","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2606.25450","title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.14816","title":"Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.19291","title":"Why Pretraining Fails to Share Cross-Lingual Knowledge","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.05387","title":"GNN-CB: A Graph Neural Network Competition Benchmark for Human and LLM Evaluation","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}