{"total":25,"rows":[{"id":"2401.04621","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","created":"2024-01-09","cited_by_count":76,"area":null},{"id":"2312.15698","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","created":"2023-12-25","cited_by_count":50,"area":null},{"id":"2407.07959","title":"Source Code Summarization in the Era of Large Language Models","created":"2024-07-09","cited_by_count":31,"area":null},{"id":"2406.07411","title":"VersiCode: Towards Version-controllable Code Generation","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2402.06598","title":"CigaR: Cost-efficient Program Repair with LLMs","created":"2024-02-09","cited_by_count":15,"area":null},{"id":"2403.10433","title":"AI-enhanced Collective Intelligence","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2312.14856","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code","created":"2023-12-22","cited_by_count":9,"area":null},{"id":"2407.01646","title":"ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization","created":"2024-07-01","cited_by_count":8,"area":null},{"id":"2409.10033","title":"Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs","created":"2024-09-16","cited_by_count":7,"area":null},{"id":"2501.04848","title":"Exploring Large Language Models for Semantic Analysis and Categorization of Android Malware","created":"2025-01-08","cited_by_count":6,"area":null},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2405.13932","title":"Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2503.09217","title":"Evaluating the Generalizability of LLMs in Automated Program Repair","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2507.08719","title":"Multilingual Multimodal Software Developer for Code Generation","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2408.15658","title":"An Empirical Study on Self-correcting Large Language Models for Data Science Code Generation","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2409.01944","title":"FuzzCoder: Byte-level Fuzzing Test via Large Language Model","created":"2024-09-03","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":"2407.04722","title":"A GPT-based Code Review System for Programming Language Learning","created":"2024-06-21","cited_by_count":1,"area":null},{"id":"2410.04485","title":"Exploring the Potential of Conversational Test Suite Based Program Repair on SWE-bench","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2410.18893","title":"Creating and Repairing Robot Programs in Open-World Domains","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2412.08098","title":"What You See Is Not Always What You Get: Evaluating GPT's Comprehension of Source Code","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2409.04164","title":"Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation","created":"2024-09-06","cited_by_count":0,"area":null},{"id":"2601.02045","title":"The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2604.21579","title":"A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair","created":"2026-04-23","cited_by_count":0,"area":null}],"next_cursor":null}