{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"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":"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":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"1906.04908","title":"SPoC: Search-based Pseudocode to Code","created":"2019-06-12","cited_by_count":176},{"id":"1901.01808","title":"SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair","created":"2018-12-24","cited_by_count":145},{"id":"2312.04724","title":"Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models","created":"2023-12-07","cited_by_count":138},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121},{"id":"2112.02125","title":"Examining Zero-Shot Vulnerability Repair with Large Language Models","created":"2021-12-03","cited_by_count":105},{"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":"2302.07427","title":"Studying the effect of AI Code Generators on Supporting Novice Learners in Introductory Programming","created":"2023-02-15","cited_by_count":89},{"id":"2404.13161","title":"CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models","created":"2024-04-19","cited_by_count":89},{"id":"2310.00658","title":"The Robots are Here: Navigating the Generative AI Revolution in Computing Education","created":"2023-10-01","cited_by_count":86},{"id":"2401.04621","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","created":"2024-01-09","cited_by_count":76},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71},{"id":"2003.13848","title":"Code Prediction by Feeding Trees to Transformers","created":"2020-03-30","cited_by_count":70},{"id":"2303.09384","title":"LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations","created":"2023-03-16","cited_by_count":62},{"id":"2305.13712","title":"Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models","created":"2023-05-23","cited_by_count":61},{"id":"2311.16169","title":"Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities","created":"2023-11-16","cited_by_count":59},{"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":"2402.07688","title":"CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge","created":"2024-02-12","cited_by_count":55},{"id":"2202.06689","title":"CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences","created":"2022-02-14","cited_by_count":50},{"id":"2502.07049","title":"LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights","created":"2025-02-10","cited_by_count":47},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40},{"id":"2311.00889","title":"SALLM: Security Assessment of Generated Code","created":"2023-11-01","cited_by_count":39},{"id":"2004.13651","title":"Fast and Memory-Efficient Neural Code Completion","created":"2020-04-28","cited_by_count":38},{"id":"2402.11493","title":"Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation","created":"2024-02-18","cited_by_count":38},{"id":"2312.15838","title":"SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security","created":"2023-12-26","cited_by_count":37},{"id":"2406.10881","title":"Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals","created":"2024-06-16","cited_by_count":32},{"id":"2401.15232","title":"How Beginning Programmers and Code LLMs (Mis)read Each Other","created":"2024-01-26","cited_by_count":31},{"id":"2310.05292","title":"How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging","created":"2023-10-08","cited_by_count":30},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23},{"id":"2405.14383","title":"Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering","created":"2024-05-23","cited_by_count":20},{"id":"2203.09707","title":"M2TS: Multi-Scale Multi-Modal Approach Based on Transformer for Source Code Summarization","created":"2022-03-18","cited_by_count":14},{"id":"2307.08220","title":"FRANC: A Lightweight Framework for High-Quality Code Generation","created":"2023-07-17","cited_by_count":14},{"id":"2405.20441","title":"SECURE: Benchmarking Large Language Models for Cybersecurity","created":"2024-05-30","cited_by_count":14},{"id":"2410.16349","title":"Large Language Models in Computer Science Education: A Systematic Literature Review","created":"2024-10-21","cited_by_count":13},{"id":"2407.08708","title":"eyeballvul: a future-proof benchmark for vulnerability detection in the wild","created":"2024-07-11","cited_by_count":6},{"id":"2305.04940","title":"The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification","created":"2023-05-08","cited_by_count":5},{"id":"2509.25465","title":"BloomAPR: A Bloom's Taxonomy-based Framework for Assessing the Capabilities of LLM-Powered APR Solutions","created":"2025-09-29","cited_by_count":5},{"id":"2405.18062","title":"Towards Integrating Emerging AI Applications in SE Education","created":"2024-05-28","cited_by_count":4},{"id":"2312.00024","title":"Can LLMs Patch Security Issues?","created":"2023-11-13","cited_by_count":3},{"id":"1901.09286","title":"The CATS Hackathon: Creating and Refining Test Items for Cybersecurity Concept Inventories","created":"2019-01-26","cited_by_count":2},{"id":"1706.05092","title":"Creating a Cybersecurity Concept Inventory: A Status Report on the CATS Project","created":"2017-06-15","cited_by_count":1}],"next_cursor":null}