{"total":15,"rows":[{"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,"area":null},{"id":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36,"area":null},{"id":"2407.14044","title":"ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?","created":"2024-07-19","cited_by_count":27,"area":null},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"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":"2503.22851","title":"RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2504.15284","title":"EditLord: Learning Code Transformation Rules for Code Editing","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2503.03656","title":"Robust Learning of Diverse Code Edits","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2509.25203","title":"Generating High-Quality Datasets for Code Editing via Open-Source Language Models","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2604.17338","title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2604.27296","title":"To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2604.00392","title":"Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2606.29088","title":"Diff-Based Code Corruption using LLMs for Large-Scale Bugfix Benchmarking","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2610.13563","title":"Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution","created":"2026-10-09","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}