{"total":23,"rows":[{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"area":null},{"id":"2506.06541","title":"KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes","created":"2025-06-06","cited_by_count":33,"area":null},{"id":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"id":"2410.03131","title":"Code Comprehension then Auditing for Unsupervised LLM Evaluation","created":"2024-10-04","cited_by_count":32,"area":null},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"area":null},{"id":"2503.15554","title":"Rethinking the Evaluation of Secure Code Generation","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2505.19236","title":"Evaluating Text Creativity across Diverse Domains: A Dataset and Large Language Model Evaluator","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2601.11895","title":"DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2503.06195","title":"Human-AI Experience in Integrated Development Environments: A Systematic Literature Review","created":"2025-03-08","cited_by_count":5,"area":null},{"id":"2506.18403","title":"The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs","created":"2025-06-23","cited_by_count":5,"area":null},{"id":"2508.12358","title":"Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications","created":"2025-08-17","cited_by_count":5,"area":null},{"id":"2504.19730","title":"Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2603.00539","title":"Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement","created":"2026-02-28","cited_by_count":4,"area":null},{"id":"2502.07835","title":"Bridging LLM-Generated Code and Requirements: Reverse Generation technique and SBC Metric for Developer Insights","created":"2025-02-11","cited_by_count":3,"area":null},{"id":"2512.08810","title":"Multicalibration for LLM-based Code Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2505.11646","title":"FLOW-BENCH: Towards Conversational Generation of Enterprise Workflows","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2508.05473","title":"Embedding Alignment in Code Generation for Audio","created":"2025-08-07","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":"2601.06543","title":"Mechanism-Faithful Queueing Simulation Model Translation with Large Language Model Support","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2607.12273","title":"Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.30025","title":"Interpreting and Steering for Safe and Correct Code Generation","created":"2026-08-30","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":"2610.05094","title":"How Much Do LLM-as-a-Judge Design Choices Matter? A Systematic Comparison of Prompt Designs, Rating Scales, and Models","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}