{"total":75,"rows":[{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391,"area":null},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256,"area":null},{"id":"2308.04748","title":"Fuzz4All: Universal Fuzzing with Large Language Models","created":"2023-08-09","cited_by_count":88,"area":null},{"id":"2308.03314","title":"GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis","created":"2023-08-07","cited_by_count":65,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2309.00608","title":"Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair","created":"2023-09-01","cited_by_count":55,"area":null},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52,"area":null},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2305.14752","title":"A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification","created":"2023-05-24","cited_by_count":42,"area":null},{"id":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42,"area":null},{"id":"2404.18353","title":"How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2503.09002","title":"KNighter: Transforming Static Analysis with LLM-Synthesized Checkers","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2407.07472","title":"Rectifier: Code Translation with Corrector via LLMs","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2305.12138","title":"Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs","created":"2023-05-20","cited_by_count":19,"area":null},{"id":"2309.04142","title":"Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2308.00245","title":"The Hitchhiker's Guide to Program Analysis: A Journey with Large Language Models","created":"2023-08-01","cited_by_count":18,"area":null},{"id":"2310.05046","title":"FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models","created":"2023-10-08","cited_by_count":17,"area":null},{"id":"2405.15130","title":"OptLLM: Optimal Assignment of Queries to Large Language Models","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2402.06598","title":"CigaR: Cost-efficient Program Repair with LLMs","created":"2024-02-09","cited_by_count":15,"area":null},{"id":"2310.19813","title":"Enhancing Genetic Improvement Mutations Using Large Language Models","created":"2023-10-18","cited_by_count":13,"area":null},{"id":"2405.16792","title":"Laurel: Unblocking Automated Verification with Large Language Models","created":"2024-05-27","cited_by_count":11,"area":null},{"id":"2404.04306","title":"AuditGPT: Auditing Smart Contracts with ChatGPT","created":"2024-04-05","cited_by_count":9,"area":null},{"id":"2408.12056","title":"Enhancing Automated Program Repair with Solution Design","created":"2024-08-22","cited_by_count":8,"area":null},{"id":"2309.10419","title":"Learning from Teaching Assistants to Program with Subgoals: Exploring the Potential for AI Teaching Assistants","created":"2023-09-19","cited_by_count":7,"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":"2312.05275","title":"Exploring the Limits of ChatGPT in Software Security Applications","created":"2023-12-08","cited_by_count":6,"area":null},{"id":"2411.15501","title":"Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2403.16347","title":"ChatGPT Incorrectness Detection in Software Reviews","created":"2024-03-25","cited_by_count":5,"area":null},{"id":"2410.16655","title":"Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2510.26457","title":"SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-aware Fine-tuning","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2410.06176","title":"SC-Bench: A Large-Scale Dataset for Smart Contract Auditing","created":"2024-10-08","cited_by_count":4,"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":"2505.04852","title":"Raw Pointer Rewriting with LLMs for Translating C to Safer Rust","created":"2025-05-07","cited_by_count":4,"area":null},{"id":"2510.07740","title":"AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2605.08717","title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","created":"2026-05-09","cited_by_count":4,"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":"2512.14018","title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2512.24635","title":"DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2603.08718","title":"CktEvo: Repository-Level RTL Code Benchmark for Design Evolution","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2604.03758","title":"AutoReSpec: A Framework for Generating Specification using Large Language Models","created":"2026-04-04","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":"2501.12339","title":"Treefix: Enabling Execution with a Tree of Prefixes","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2501.12617","title":"Deep Learning-Based Identification of Inconsistent Method Names: How Far Are We?","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2504.17198","title":"Automatically Generating Rules of Malicious Software Packages via Large Language Model","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2507.15822","title":"Do AI models help produce verified bug fixes?","created":"2025-07-21","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":"2603.17826","title":"FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair","created":"2026-03-18","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":"2310.12425","title":"Automated Repair of Declarative Software Specifications in the Era of Large Language Models","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2408.08619","title":"PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code","created":"2024-08-16","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":"2504.15637","title":"DR.FIX: Automatically Fixing Data Races at Industry Scale","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2506.13182","title":"From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2509.23835","title":"HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2601.04540","title":"AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2603.27333","title":"ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2605.00382","title":"Social Bias in LLM-Generated Code: Benchmark and Mitigation","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2608.14065","title":"Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2312.08055","title":"Breaking the Silence: the Threats of Using LLMs in Software Engineering","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2507.13629","title":"Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2508.16071","title":"From Benchmark Data To Applicable Program Repair: An Experience Report","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2510.01453","title":"The Command Line GUIde: Graphical Interfaces from Man Pages via AI","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.10010","title":"SLEAN: Simple Lightweight Ensemble Analysis Network for Multi-Provider LLM Coordination: Design, Implementation, and Vibe Coding Bug Investigation Case Study","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2603.13640","title":"SemRep: Generative Code Representation Learning with Code Transformations","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.06723","title":"Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.12108","title":"LLM-Based Automated Diagnosis Of Integration Test Failures At Google","created":"2026-04-13","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},{"id":"2605.17450","title":"ContraFix: Skill-Enhanced Contrastive Runtime Analysis for Vulnerability Repair","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2607.25873","title":"How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.14913","title":"Externalizing Requirement-to-Repair Artifacts as Observable Traces for LLM-Based Program Repair","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.29410","title":"Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code?","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}