{"total":16,"rows":[{"id":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"id":"2505.16222","title":"Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","created":"2025-05-22","cited_by_count":18,"area":null},{"id":"2503.17502","title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","created":"2025-03-21","cited_by_count":16,"area":null},{"id":"2508.01473","title":"TreeDiff: AST-Guided Code Generation with Diffusion LLMs","created":"2025-08-02","cited_by_count":11,"area":null},{"id":"2504.12589","title":"Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer","created":"2025-04-17","cited_by_count":4,"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":"2604.16790","title":"Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2607.12885","title":"LLM Judges Can Be Too Generous When There Is No Reference Answer","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2606.06454","title":"Scaffold, Not Vocabulary? A Controlled, Two-Tier, Pre-Registered Study of a Popperian Code-Generation Skill","created":"2026-06-04","cited_by_count":3,"area":null},{"id":"2412.07019","title":"Assessing the Impact of Conspiracy Theories Using Large Language Models","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2510.03914","title":"Refactoring with LLMs: Bridging Human Expertise and Machine Understanding","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2512.20159","title":"Benchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2507.19390","title":"ReCatcher: Towards LLMs Regression Testing for Code Generation","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2509.06402","title":"NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2512.16272","title":"Beyond Blind Spots: Analytic Hints for Mitigating LLM-Based Evaluation Pitfalls","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2605.25658","title":"AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization","created":"2026-05-25","cited_by_count":0,"area":null}],"next_cursor":null}