{"list":"other","total":101,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"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":"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":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"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":"1712.03141","title":"Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning","created":"2017-12-08","cited_by_count":414},{"id":"1911.00068","title":"Confident Learning: Estimating Uncertainty in Dataset Labels","created":"2019-10-31","cited_by_count":413},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2202.13169","title":"A Systematic Evaluation of Large Language Models of Code","created":"2022-02-26","cited_by_count":363},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207},{"id":"2307.07221","title":"Software Testing with Large Language Models: Survey, Landscape, and Vision","created":"2023-07-14","cited_by_count":166},{"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":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"2201.11227","title":"Synchromesh: Reliable code generation from pre-trained language models","created":"2022-01-26","cited_by_count":156},{"id":"2206.15331","title":"GitHub Copilot AI pair programmer: Asset or Liability?","created":"2022-06-30","cited_by_count":152},{"id":"2009.07235","title":"Deep Learning based Vulnerability Detection: Are We There Yet?","created":"2020-09-03","cited_by_count":144},{"id":"2007.02220","title":"You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion","created":"2020-07-05","cited_by_count":131},{"id":"1807.07838","title":"TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time","created":"2018-07-20","cited_by_count":108},{"id":"2112.02125","title":"Examining Zero-Shot Vulnerability Repair with Large Language Models","created":"2021-12-03","cited_by_count":105},{"id":"2112.02969","title":"Jigsaw: Large Language Models meet Program Synthesis","created":"2021-12-06","cited_by_count":103},{"id":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103},{"id":"1811.07234","title":"Improving Automatic Source Code Summarization via Deep Reinforcement Learning","created":"2018-11-17","cited_by_count":100},{"id":"2002.11985","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","created":"2020-02-27","cited_by_count":96},{"id":"2210.14306","title":"Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming","created":"2022-10-25","cited_by_count":91},{"id":"2307.12596","title":"Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues","created":"2023-07-24","cited_by_count":79},{"id":"2303.16749","title":"Improving Code Generation by Training with Natural Language Feedback","created":"2023-03-28","cited_by_count":76},{"id":"2201.08698","title":"Natural Attack for Pre-trained Models of Code","created":"2022-01-21","cited_by_count":75},{"id":"2206.08451","title":"I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences","created":"2022-06-16","cited_by_count":75},{"id":"1603.06744","title":"Latent Predictor Networks for Code Generation","created":"2016-03-22","cited_by_count":73},{"id":"2008.05221","title":"Compression of Deep Learning Models for Text: A Survey","created":"2020-08-12","cited_by_count":64},{"id":"2302.00438","title":"On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot","created":"2023-02-01","cited_by_count":64},{"id":"2106.10478","title":"Vulnerability Detection with Fine-grained Interpretations","created":"2021-06-19","cited_by_count":56},{"id":"2305.18607","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","created":"2023-05-29","cited_by_count":52},{"id":"2202.06840","title":"What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code","created":"2022-02-14","cited_by_count":50},{"id":"2102.07995","title":"D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis","created":"2021-02-16","cited_by_count":49},{"id":"2301.02496","title":"Stealthy Backdoor Attack for Code Models","created":"2023-01-06","cited_by_count":49},{"id":"2107.07112","title":"On the Evaluation of Neural Code Summarization","created":"2021-07-15","cited_by_count":48},{"id":"2110.12925","title":"CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning","created":"2021-10-25","cited_by_count":47},{"id":"2303.02552","title":"An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry","created":"2023-03-05","cited_by_count":47},{"id":"2212.08109","title":"An Empirical Study of Deep Learning Models for Vulnerability Detection","created":"2022-12-15","cited_by_count":46},{"id":"2002.03043","title":"Semantic Robustness of Models of Source Code","created":"2020-02-07","cited_by_count":45},{"id":"2008.01566","title":"On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations","created":"2020-07-31","cited_by_count":44},{"id":"1708.09492","title":"Automatically Generating Commit Messages from Diffs using Neural Machine Translation","created":"2017-08-30","cited_by_count":42},{"id":"2003.05620","title":"CC2Vec: Distributed Representations of Code Changes","created":"2020-03-12","cited_by_count":39},{"id":"2004.13651","title":"Fast and Memory-Efficient Neural Code Completion","created":"2020-04-28","cited_by_count":38},{"id":"2011.14597","title":"A Survey on Deep Learning for Software Engineering","created":"2020-11-30","cited_by_count":38},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38},{"id":"2203.11852","title":"Representation Bias in Data: A Survey on Identification and Resolution Techniques","created":"2022-03-22","cited_by_count":37},{"id":"1909.06727","title":"An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms","created":"2019-09-15","cited_by_count":35},{"id":"2009.06520","title":"A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research","created":"2020-09-14","cited_by_count":35},{"id":"2208.08289","title":"CCTEST: Testing and Repairing Code Completion Systems","created":"2022-08-17","cited_by_count":35},{"id":"2308.14401","title":"CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models","created":"2023-08-28","cited_by_count":34},{"id":"2202.06649","title":"On the Importance of Building High-quality Training Datasets for Neural Code Search","created":"2022-02-14","cited_by_count":30},{"id":"2112.02268","title":"Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding","created":"2021-12-04","cited_by_count":28},{"id":"2302.04026","title":"An Empirical Comparison of Pre-Trained Models of Source Code","created":"2023-02-08","cited_by_count":25},{"id":"2306.04930","title":"When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming","created":"2023-06-08","cited_by_count":25},{"id":"2206.14390","title":"Diet Code Is Healthy: Simplifying Programs for Pre-trained Models of Code","created":"2022-06-29","cited_by_count":24},{"id":"2202.02326","title":"Towards Training Reproducible Deep Learning Models","created":"2022-02-04","cited_by_count":23},{"id":"2108.00213","title":"Adversarial Robustness of Deep Code Comment Generation","created":"2021-07-31","cited_by_count":22},{"id":"2207.05579","title":"Are We Building on the Rock? On the Importance of Data Preprocessing for Code Summarization","created":"2022-07-12","cited_by_count":22},{"id":"2208.07120","title":"Compressing Pre-trained Models of Code into 3 MB","created":"2022-08-15","cited_by_count":21},{"id":"2011.04542","title":"Learning Autocompletion from Real-World Datasets","created":"2020-11-09","cited_by_count":20},{"id":"2304.05216","title":"Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond","created":"2023-04-11","cited_by_count":20},{"id":"2101.04401","title":"Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps","created":"2021-01-12","cited_by_count":19},{"id":"2309.04142","title":"Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps","created":"2023-09-08","cited_by_count":19},{"id":"2008.10707","title":"Patching as Translation: the Data and the Metaphor","created":"2020-08-24","cited_by_count":18},{"id":"2112.12591","title":"Black-Box Testing of Deep Neural Networks Through Test Case Diversity","created":"2021-12-20","cited_by_count":18},{"id":"2309.07639","title":"Your Code Secret Belongs to Me: Neural Code Completion Tools Can Memorize Hard-Coded Credentials","created":"2023-09-14","cited_by_count":17},{"id":"2006.14244","title":"On the Replicability and Reproducibility of Deep Learning in Software Engineering","created":"2020-06-25","cited_by_count":16},{"id":"2301.09072","title":"ContraBERT: Enhancing Code Pre-trained Models via Contrastive Learning","created":"2023-01-22","cited_by_count":16},{"id":"2302.04030","title":"CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models","created":"2023-02-08","cited_by_count":16},{"id":"2111.10793","title":"Challenging Machine Learning-based Clone Detectors via Semantic-preserving Code Transformations","created":"2021-11-21","cited_by_count":15},{"id":"2010.07987","title":"Empirical Study of Transformers for Source Code","created":"2020-10-15","cited_by_count":13},{"id":"2308.05362","title":"FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis","created":"2023-08-10","cited_by_count":12},{"id":"2208.10091","title":"Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generation","created":"2022-08-22","cited_by_count":11},{"id":"2207.11104","title":"Two Sides of the Same Coin: Exploiting the Impact of Identifiers in Neural Code Comprehension","created":"2022-07-22","cited_by_count":10},{"id":"2303.00732","title":"R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents","created":"2023-03-01","cited_by_count":10},{"id":"2005.04970","title":"A Performance-Sensitive Malware Detection System Using Deep Learning on Mobile Devices","created":"2020-05-11","cited_by_count":9},{"id":"2102.12007","title":"Practitioners' Perceptions of the Goals and Visual Explanations of Defect Prediction Models","created":"2021-02-24","cited_by_count":9},{"id":"2308.00683","title":"CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code","created":"2023-08-01","cited_by_count":9},{"id":"2310.07958","title":"Towards Causal Deep Learning for Vulnerability Detection","created":"2023-10-12","cited_by_count":9},{"id":"2012.01614","title":"Explainable AI for Software Engineering","created":"2020-12-03","cited_by_count":8},{"id":"2104.14671","title":"SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics","created":"2021-04-29","cited_by_count":8},{"id":"2302.03482","title":"Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models","created":"2023-02-07","cited_by_count":8},{"id":"2305.17047","title":"Towards More Realistic Evaluation for Neural Test Oracle Generation","created":"2023-05-26","cited_by_count":8}],"next_cursor":"100"}