{"list":"other","total":61,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"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":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"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":"2202.13169","title":"A Systematic Evaluation of Large Language Models of Code","created":"2022-02-26","cited_by_count":363},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337},{"id":"2211.03622","title":"Do Users Write More Insecure Code with AI Assistants?","created":"2022-11-07","cited_by_count":192},{"id":"2310.03533","title":"Large Language Models for Software Engineering: Survey and Open Problems","created":"2023-10-05","cited_by_count":181},{"id":"2308.01861","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation","created":"2023-08-03","cited_by_count":168},{"id":"2206.15331","title":"GitHub Copilot AI pair programmer: Asset or Liability?","created":"2022-06-30","cited_by_count":152},{"id":"2210.14179","title":"Practical Program Repair in the Era of Large Pre-trained Language Models","created":"2022-10-25","cited_by_count":133},{"id":"1904.02792","title":"Unifying Human and Statistical Evaluation for Natural Language Generation","created":"2019-04-04","cited_by_count":127},{"id":"2212.11140","title":"Benchmarking Large Language Models for Automated Verilog RTL Code Generation","created":"2022-12-13","cited_by_count":115},{"id":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103},{"id":"1811.02549","title":"Language GANs Falling Short","created":"2018-11-06","cited_by_count":97},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97},{"id":"2302.07080","title":"The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Development","created":"2023-02-14","cited_by_count":96},{"id":"2201.08698","title":"Natural Attack for Pre-trained Models of Code","created":"2022-01-21","cited_by_count":75},{"id":"2205.10583","title":"Automated Repair of Programs from Large Language Models","created":"2022-05-21","cited_by_count":71},{"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":"1910.07517","title":"Adversarial Examples for Models of Code","created":"2019-10-15","cited_by_count":63},{"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":"2308.01240","title":"Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation","created":"2023-08-02","cited_by_count":50},{"id":"2208.05446","title":"CoditT5: Pretraining for Source Code and Natural Language Editing","created":"2022-08-10","cited_by_count":45},{"id":"2104.03820","title":"Perfection Not Required? Human-AI Partnerships in Code Translation","created":"2021-04-08","cited_by_count":42},{"id":"2208.06213","title":"What is it like to program with artificial intelligence?","created":"2022-08-12","cited_by_count":39},{"id":"2208.08289","title":"CCTEST: Testing and Repairing Code Completion Systems","created":"2022-08-17","cited_by_count":35},{"id":"2307.04346","title":"Can Large Language Models Write Good Property-Based Tests?","created":"2023-07-10","cited_by_count":31},{"id":"2310.14053","title":"Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain","created":"2023-10-21","cited_by_count":31},{"id":"2310.08879","title":"A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repair","created":"2023-10-13","cited_by_count":29},{"id":"2308.15276","title":"Large Language Models in Fault Localisation","created":"2023-08-29","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":"2103.11882","title":"Generating Adversarial Computer Programs using Optimized Obfuscations","created":"2021-03-18","cited_by_count":22},{"id":"2312.00894","title":"Leveraging Large Language Models to Improve REST API Testing","created":"2023-12-01","cited_by_count":20},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16},{"id":"2210.14699","title":"Piloting Copilot, Codex, and StarCoder2: Hot Temperature, Cold Prompts, or Black Magic?","created":"2022-10-26","cited_by_count":14},{"id":"2211.15844","title":"How Important are Good Method Names in Neural Code Generation? A Model Robustness Perspective","created":"2022-11-29","cited_by_count":11},{"id":"2308.04898","title":"An Empirical Study on Using Large Language Models to Analyze Software Supply Chain Security Failures","created":"2023-08-09","cited_by_count":11},{"id":"2301.02412","title":"Code Difference Guided Adversarial Example Generation for Deep Code Models","created":"2023-01-06","cited_by_count":9},{"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":"2306.02230","title":"Prompt Sapper: LLM-Empowered Software Engineering Infrastructure for AI-Native Services","created":"2023-06-04","cited_by_count":5},{"id":"2106.09242","title":"CoCoFuzzing: Testing Neural Code Models with Coverage-Guided Fuzzing","created":"2021-06-17","cited_by_count":4},{"id":"2209.01766","title":"Exploring the Verifiability of Code Generated by GitHub Copilot","created":"2022-09-05","cited_by_count":4},{"id":"2211.10623","title":"Do Pre-trained Language Models Indeed Understand Software Engineering Tasks?","created":"2022-11-19","cited_by_count":4},{"id":"2308.13319","title":"COCO: Testing Code Generation Systems via Concretized Instructions","created":"2023-08-25","cited_by_count":4},{"id":"2310.16253","title":"ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair","created":"2023-10-25","cited_by_count":4},{"id":"2106.11629","title":"On Adversarial Robustness of Synthetic Code Generation","created":"2021-06-22","cited_by_count":3},{"id":"2203.03289","title":"$\\mu$BERT: Mutation Testing using Pre-Trained Language Models","created":"2022-03-07","cited_by_count":3},{"id":"2211.11711","title":"CLAWSAT: Towards Both Robust and Accurate Code Models","created":"2022-11-21","cited_by_count":2},{"id":"2301.07775","title":"Automatically Reproducing Android Bug Reports Using Natural Language Processing and Reinforcement Learning","created":"2023-01-18","cited_by_count":1}],"next_cursor":null}