{"total":67,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"area":null},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131,"area":null},{"id":"2302.05527","title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","created":"2023-02-10","cited_by_count":102,"area":null},{"id":"2402.16694","title":"HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64,"area":null},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2403.15452","title":"What Are Tools Anyway? A Survey from the Language Model Perspective","created":"2024-03-18","cited_by_count":54,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"area":null},{"id":"2403.08604","title":"Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study","created":"2024-03-13","cited_by_count":44,"area":null},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2507.17773","title":"MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation","created":"2025-07-20","cited_by_count":38,"area":null},{"id":"2402.07844","title":"Mercury: A Code Efficiency Benchmark for Code Large Language Models","created":"2024-02-12","cited_by_count":35,"area":null},{"id":"2408.14354","title":"SWE-bench-java: A GitHub Issue Resolving Benchmark for Java","created":"2024-08-26","cited_by_count":34,"area":null},{"id":"2308.10462","title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models","created":"2023-08-21","cited_by_count":28,"area":null},{"id":"2312.11444","title":"An In-depth Look at Gemini's Language Abilities","created":"2023-12-18","cited_by_count":28,"area":null},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","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":"2308.16458","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","created":"2023-08-31","cited_by_count":25,"area":null},{"id":"2403.04814","title":"Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks","created":"2024-03-07","cited_by_count":25,"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":"2309.17446","title":"L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models","created":"2023-09-29","cited_by_count":22,"area":null},{"id":"2406.11927","title":"On the Impacts of Contexts on Repository-Level Code Generation","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2408.13204","title":"DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation","created":"2024-08-23","cited_by_count":21,"area":null},{"id":"2402.19475","title":"The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?","created":"2024-02-29","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":"2408.11081","title":"What can Large Language Models Capture about Code Functional Equivalence?","created":"2024-08-20","cited_by_count":14,"area":null},{"id":"2406.18294","title":"Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs","created":"2024-06-26","cited_by_count":13,"area":null},{"id":"2505.20538","title":"AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy","created":"2025-05-26","cited_by_count":13,"area":null},{"id":"2503.13733","title":"CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2402.19431","title":"Compositional API Recommendation for Library-Oriented Code Generation","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2406.12902","title":"JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2410.23074","title":"Multi-Programming Language Sandbox for LLMs","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2404.10155","title":"The Fault in our Stars: Quality Assessment of Code Generation Benchmarks","created":"2024-04-15","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":"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":"2312.13876","title":"Capture the Flag: Uncovering Data Insights with Large Language Models","created":"2023-12-21","cited_by_count":4,"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":"2409.16819","title":"CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2505.23060","title":"Self-Correcting Code Generation Using Small Language Models","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2408.11987","title":"SimBench: A Framework for Evaluating and Diagnosing LLM-Based Digital-Twin Generation for Multi-Physics Simulation","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2409.13551","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","created":"2024-09-20","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":"2507.08719","title":"Multilingual Multimodal Software Developer for Code Generation","created":"2025-07-11","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":"2407.10626","title":"NoviCode: Generating Programs from Natural Language Utterances by Novices","created":"2024-07-15","cited_by_count":2,"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":"2409.03402","title":"Game On: Towards Language Models as RL Experimenters","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2507.15501","title":"ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution","created":"2025-07-21","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":"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":"2604.10520","title":"ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2312.15157","title":"CodeScholar: Growing Idiomatic Code Examples","created":"2023-12-23","cited_by_count":0,"area":null},{"id":"2604.07755","title":"An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2607.26457","title":"DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning","created":"2026-07-29","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},{"id":"2610.20027","title":"LintEval: Benchmarking LLMs on Linter-Guided File Refactoring","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}