{"list":"other","total":51,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"2404.18796","title":"Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models","created":"2024-04-29","cited_by_count":326},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"id":"2302.06590","title":"The Impact of AI on Developer Productivity: Evidence from GitHub Copilot","created":"2023-02-13","cited_by_count":274},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"2206.15000","title":"Grounded Copilot: How Programmers Interact with Code-Generating Models","created":"2022-06-30","cited_by_count":218},{"id":"2406.10216","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","created":"2024-06-14","cited_by_count":142},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105},{"id":"2302.07080","title":"The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Development","created":"2023-02-14","cited_by_count":96},{"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":"2303.17125","title":"A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges","created":"2023-03-30","cited_by_count":75},{"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":"2408.16498","title":"A Survey on Evaluating Large Language Models in Code Generation Tasks","created":"2024-08-29","cited_by_count":44},{"id":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41},{"id":"2410.22821","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","created":"2024-10-30","cited_by_count":34},{"id":"2502.18658","title":"Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support","created":"2025-02-25","cited_by_count":34},{"id":"2409.14664","title":"Direct Judgement Preference Optimization","created":"2024-09-23","cited_by_count":33},{"id":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33},{"id":"2507.08149","title":"Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows","created":"2025-07-10","cited_by_count":28},{"id":"2501.17195","title":"Atla Selene Mini: A General Purpose Evaluation Model","created":"2025-01-27","cited_by_count":27},{"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},{"id":"2502.09328","title":"Copilot Arena: A Platform for Code LLM Evaluation in the Wild","created":"2025-02-13","cited_by_count":26},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26},{"id":"2404.06503","title":"Comparing Two Model Designs for Clinical Note Generation; Is an LLM a Useful Evaluator of Consistency?","created":"2024-04-09","cited_by_count":20},{"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":"2306.11722","title":"Automated Grading and Feedback Tools for Programming Education: A Systematic Review","created":"2023-06-20","cited_by_count":17},{"id":"2410.12851","title":"VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models","created":"2024-10-10","cited_by_count":17},{"id":"2512.07921","title":"DeepCode: Open Agentic Coding","created":"2025-12-08","cited_by_count":16},{"id":"2501.08774","title":"How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering","created":"2025-01-15","cited_by_count":15},{"id":"2511.04486","title":"EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits","created":"2025-11-06","cited_by_count":13},{"id":"2511.08301","title":"Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learning","created":"2025-11-11","cited_by_count":5},{"id":"2409.12967","title":"How Consistent Are Humans When Grading Programming Assignments?","created":"2024-09-02","cited_by_count":4},{"id":"2504.00409","title":"Semantic Mastery: Enhancing LLMs with Advanced Natural Language Understanding","created":"2025-04-01","cited_by_count":4},{"id":"2508.12285","title":"\"My productivity is boosted, but ...\" Demystifying Users' Perception on AI Coding Assistants","created":"2025-08-17","cited_by_count":4},{"id":"2512.19926","title":"Developers' Experience with Generative AI -- First Insights from an Empirical Mixed-Methods Field Study","created":"2025-12-22","cited_by_count":4},{"id":"2506.13270","title":"Screen Reader Programmers in the Vibe Coding Era: Adaptation, Empowerment, and New Accessibility Landscape","created":"2025-06-16","cited_by_count":3},{"id":"1705.11087","title":"What to Fix? Distinguishing between design and non-design rules in automated tools","created":"2017-05-31","cited_by_count":2},{"id":"2503.02833","title":"The Shift from Writing to Pruning Software: A Bonsai-Inspired IDE for Reshaping AI Generated Code","created":"2025-03-04","cited_by_count":2},{"id":"2511.18849","title":"Pre-Filtering Code Suggestions using Developer Behavioral Telemetry to Optimize LLM-Assisted Programming","created":"2025-11-24","cited_by_count":2},{"id":"1909.09682","title":"Do internal software quality tools measure validated metrics?","created":"2019-09-20","cited_by_count":1},{"id":"2304.13451","title":"A Systematic Mapping Study of Code Quality in Education -- with Complete Bibliography","created":"2023-04-26","cited_by_count":1},{"id":"2410.11768","title":"Evaluating Software Contribution Quality: Time-to-Modification Theory","created":"2024-10-15","cited_by_count":1},{"id":"2507.17743","title":"Educational Insights from Code: Mapping Learning Challenges in Object-Oriented Programming through Code-Based Evidence","created":"2025-07-23","cited_by_count":1}],"next_cursor":null}