{"list":"other","total":53,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2302.06590","title":"The Impact of AI on Developer Productivity: Evidence from GitHub Copilot","created":"2023-02-13","cited_by_count":274},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238},{"id":"2307.08177","title":"Using an LLM to Help With Code Understanding","created":"2023-07-17","cited_by_count":228},{"id":"2206.15000","title":"Grounded Copilot: How Programmers Interact with Code-Generating Models","created":"2022-06-30","cited_by_count":218},{"id":"2002.04087","title":"Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy","created":"2020-02-10","cited_by_count":183},{"id":"2308.01861","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation","created":"2023-08-03","cited_by_count":168},{"id":"2405.06087","title":"When combinations of humans and AI are useful: A systematic review and meta-analysis","created":"2024-05-09","cited_by_count":106},{"id":"2507.09089","title":"Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity","created":"2025-07-12","cited_by_count":101},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92},{"id":"2210.14306","title":"Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming","created":"2022-10-25","cited_by_count":91},{"id":"2506.00641","title":"AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents","created":"2025-05-31","cited_by_count":90},{"id":"2404.00599","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-03-31","cited_by_count":72},{"id":"2502.06193","title":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","created":"2025-02-10","cited_by_count":67},{"id":"2410.03981","title":"A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages","created":"2024-10-04","cited_by_count":66},{"id":"2412.15701","title":"Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration","created":"2024-12-20","cited_by_count":65},{"id":"2304.02491","title":"\"It's Weird That it Knows What I Want\": Usability and Interactions with Copilot for Novice Programmers","created":"2023-04-05","cited_by_count":64},{"id":"2506.11928","title":"LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?","created":"2025-06-13","cited_by_count":55},{"id":"2202.08821","title":"Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairness","created":"2022-02-17","cited_by_count":45},{"id":"2312.01639","title":"On the Effectiveness of Large Language Models in Domain-Specific Code Generation","created":"2023-12-04","cited_by_count":44},{"id":"2404.00029","title":"Complementarity in Human-AI Collaboration: Concept, Sources, and Evidence","created":"2024-03-21","cited_by_count":35},{"id":"2504.04633","title":"M$^2$IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering","created":"2025-04-06","cited_by_count":35},{"id":"2303.09224","title":"Human-AI Collaboration: The Effect of AI Delegation on Human Task Performance and Task Satisfaction","created":"2023-03-16","cited_by_count":32},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30},{"id":"2407.19098","title":"Evaluating Human-AI Collaboration: A Review and Methodological Framework","created":"2024-07-09","cited_by_count":27},{"id":"2405.17814","title":"FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models","created":"2024-05-28","cited_by_count":22},{"id":"2410.12381","title":"HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks","created":"2024-10-16","cited_by_count":20},{"id":"2410.12944","title":"How much does AI impact development speed? An enterprise-based randomized controlled trial","created":"2024-10-16","cited_by_count":20},{"id":"2406.17910","title":"Transforming Software Development: Evaluating the Efficiency and Challenges of GitHub Copilot in Real-World Projects","created":"2024-06-25","cited_by_count":18},{"id":"2507.16587","title":"On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization","created":"2025-07-22","cited_by_count":18},{"id":"2203.05053","title":"Optical Flow Training under Limited Label Budget via Active Learning","created":"2022-03-09","cited_by_count":14},{"id":"2406.00560","title":"The Role of Generative AI in Software Development Productivity: A Pilot Case Study","created":"2024-06-01","cited_by_count":14},{"id":"2507.19315","title":"AutoPCR: Automated Phenotype Concept Recognition by Prompting","created":"2025-07-25","cited_by_count":10},{"id":"1901.05771","title":"Time Pressure in Software Engineering: A Systematic Review","created":"2019-01-17","cited_by_count":8},{"id":"2501.13282","title":"Experience with GitHub Copilot for Developer Productivity at Zoominfo","created":"2025-01-23","cited_by_count":8},{"id":"2509.22854","title":"Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention","created":"2025-09-26","cited_by_count":8},{"id":"2511.23402","title":"Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning","created":"2025-11-28","cited_by_count":8},{"id":"2511.10865","title":"Towards a Human-in-the-Loop Framework for Reliable Patch Evaluation Using an LLM-as-a-Judge","created":"2025-11-14","cited_by_count":6},{"id":"2409.11022","title":"DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition","created":"2024-09-17","cited_by_count":5},{"id":"2503.06195","title":"Human-AI Experience in Integrated Development Environments: A Systematic Literature Review","created":"2025-03-08","cited_by_count":5},{"id":"2403.14592","title":"Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals","created":"2024-03-21","cited_by_count":2},{"id":"2409.00875","title":"The Impact of Generative AI-Powered Code Generation Tools on Software Engineer Hiring: Recruiters' Experiences, Perceptions, and Strategies","created":"2024-09-02","cited_by_count":2}],"next_cursor":null}