{"list":"other","total":95,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"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},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2108.09293","title":"Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions","created":"2021-08-20","cited_by_count":431},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282},{"id":"2006.03511","title":"Unsupervised Translation of Programming Languages","created":"2020-06-05","cited_by_count":263},{"id":"2105.12655","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","created":"2021-05-25","cited_by_count":200},{"id":"2211.03622","title":"Do Users Write More Insecure Code with AI Assistants?","created":"2022-11-07","cited_by_count":192},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183},{"id":"1805.08949","title":"Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow","created":"2018-05-23","cited_by_count":165},{"id":"2201.11227","title":"Synchromesh: Reliable code generation from pre-trained language models","created":"2022-01-26","cited_by_count":156},{"id":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155},{"id":"2009.07235","title":"Deep Learning based Vulnerability Detection: Are We There Yet?","created":"2020-09-03","cited_by_count":144},{"id":"2403.18624","title":"Vulnerability Detection with Code Language Models: How Far Are We?","created":"2024-03-27","cited_by_count":139},{"id":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112},{"id":"2304.00409","title":"DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection","created":"2023-04-01","cited_by_count":102},{"id":"2312.12575","title":"LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks","created":"2023-12-19","cited_by_count":97},{"id":"1802.03691","title":"Tree-to-tree Neural Networks for Program Translation","created":"2018-02-11","cited_by_count":93},{"id":"2107.08760","title":"CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software","created":"2021-07-19","cited_by_count":91},{"id":"2212.09248","title":"Natural Language to Code Generation in Interactive Data Science Notebooks","created":"2022-12-19","cited_by_count":87},{"id":"2110.06773","title":"Leveraging Automated Unit Tests for Unsupervised Code Translation","created":"2021-10-13","cited_by_count":82},{"id":"2401.04621","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","created":"2024-01-09","cited_by_count":76},{"id":"2402.16667","title":"RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation","created":"2024-02-26","cited_by_count":70},{"id":"1805.11683","title":"DeepBugs: A Learning Approach to Name-based Bug Detection","created":"2018-04-30","cited_by_count":65},{"id":"2301.02344","title":"TrojanPuzzle: Covertly Poisoning Code-Suggestion Models","created":"2023-01-06","cited_by_count":60},{"id":"2108.11590","title":"AVATAR: A Parallel Corpus for Java-Python Program Translation","created":"2021-08-26","cited_by_count":59},{"id":"2311.16169","title":"Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities","created":"2023-11-16","cited_by_count":59},{"id":"2401.16185","title":"LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning","created":"2024-01-29","cited_by_count":59},{"id":"2410.07331","title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","created":"2024-10-09","cited_by_count":58},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57},{"id":"2404.14646","title":"Exploring and Unleashing the Power of Large Language Models in Automated Code Translation","created":"2024-04-23","cited_by_count":57},{"id":"2206.08474","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","created":"2022-06-16","cited_by_count":56},{"id":"2302.04012","title":"CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models","created":"2023-02-08","cited_by_count":55},{"id":"2206.00052","title":"CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models","created":"2022-05-31","cited_by_count":53},{"id":"2301.05456","title":"Data Quality for Software Vulnerability Datasets","created":"2023-01-13","cited_by_count":51},{"id":"1901.09102","title":"On Learning Meaningful Code Changes via Neural Machine Translation","created":"2019-01-25","cited_by_count":50},{"id":"2308.09895","title":"Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs","created":"2023-08-19","cited_by_count":45},{"id":"2401.15468","title":"Large Language Model for Vulnerability Detection: Emerging Results and Future Directions","created":"2024-01-27","cited_by_count":45},{"id":"2207.03578","title":"Code Translation with Compiler Representations","created":"2022-06-30","cited_by_count":42},{"id":"2302.06144","title":"SkCoder: A Sketch-based Approach for Automatic Code Generation","created":"2023-02-13","cited_by_count":40},{"id":"2311.08588","title":"CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation","created":"2023-11-14","cited_by_count":39},{"id":"2405.11514","title":"Towards Translating Real-World Code with LLMs: A Study of Translating to Rust","created":"2024-05-19","cited_by_count":35},{"id":"2412.06176","title":"AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement","created":"2024-12-09","cited_by_count":35},{"id":"2307.02192","title":"The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification","created":"2023-07-05","cited_by_count":34},{"id":"2402.17230","title":"Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities","created":"2024-02-27","cited_by_count":31},{"id":"2306.17193","title":"Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection","created":"2023-06-28","cited_by_count":30},{"id":"2312.11658","title":"Traces of Memorisation in Large Language Models for Code","created":"2023-12-18","cited_by_count":29},{"id":"2406.12415","title":"MegaVul: A C/C++ Vulnerability Dataset with Comprehensive Code Representation","created":"2024-06-18","cited_by_count":27},{"id":"2308.08961","title":"On the Evaluation of Neural Code Translation: Taxonomy and Benchmark","created":"2023-08-17","cited_by_count":23},{"id":"2404.02056","title":"Multitask-based Evaluation of Open-Source LLM on Software Vulnerability","created":"2024-04-02","cited_by_count":23},{"id":"2404.18852","title":"VERT: Verified Equivalent Rust Transpilation with Large Language Models as Few-Shot Learners","created":"2024-04-29","cited_by_count":20},{"id":"2504.20115","title":"AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers","created":"2025-04-28","cited_by_count":20},{"id":"2212.08108","title":"Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection","created":"2022-12-15","cited_by_count":19},{"id":"2410.20527","title":"CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming","created":"2024-10-27","cited_by_count":19},{"id":"2504.15254","title":"CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation","created":"2025-04-21","cited_by_count":19},{"id":"2405.15614","title":"Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study","created":"2024-05-24","cited_by_count":17},{"id":"2301.09072","title":"ContraBERT: Enhancing Code Pre-trained Models via Contrastive Learning","created":"2023-01-22","cited_by_count":16},{"id":"2408.11006","title":"Security Attacks on LLM-based Code Completion Tools","created":"2024-08-20","cited_by_count":16},{"id":"2412.14234","title":"Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis","created":"2024-12-18","cited_by_count":16},{"id":"2310.01166","title":"Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models","created":"2023-10-02","cited_by_count":15},{"id":"2406.03003","title":"Verified Code Transpilation with LLMs","created":"2024-06-05","cited_by_count":15},{"id":"1903.06725","title":"BugSwarm: Mining and Continuously Growing a Dataset of Reproducible Failures and Fixes","created":"2019-03-15","cited_by_count":12},{"id":"2412.08035","title":"Scalable, Validated Code Translation of Entire Projects using Large Language Models","created":"2024-12-11","cited_by_count":12},{"id":"2506.11022","title":"Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox","created":"2025-05-19","cited_by_count":10},{"id":"2503.12511","title":"SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification","created":"2025-03-16","cited_by_count":9},{"id":"2506.05614","title":"Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks","created":"2025-06-05","cited_by_count":9},{"id":"2401.14886","title":"Coca: Improving and Explaining Graph Neural Network-Based Vulnerability Detection Systems","created":"2024-01-26","cited_by_count":8},{"id":"2203.09452","title":"Automated Transpilation of Imperative to Functional Code using Neural-Guided Program Synthesis (Extended Version)","created":"2022-03-17","cited_by_count":7},{"id":"2504.20612","title":"The Hidden Risks of LLM-Generated Web Application Code: A Security-Centric Evaluation of Code Generation Capabilities in Large Language Models","created":"2025-04-29","cited_by_count":7},{"id":"2310.18587","title":"Assessing and Improving Syntactic Adversarial Robustness of Pre-trained Models for Code Translation","created":"2023-10-28","cited_by_count":6},{"id":"2504.15867","title":"Inducing Vulnerable Code Generation in LLM Coding Assistants","created":"2025-04-22","cited_by_count":5},{"id":"2309.12813","title":"Automatically Testing Functional Properties of Code Translation Models","created":"2023-09-07","cited_by_count":3},{"id":"2505.10008","title":"SVA-ICL: Improving LLM-based Software Vulnerability Assessment via In-Context Learning and Information Fusion","created":"2025-05-15","cited_by_count":2}],"next_cursor":null}