{"list":"other","total":91,"rows":[{"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":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"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":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"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":"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":"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":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"2310.03533","title":"Large Language Models for Software Engineering: Survey and Open Problems","created":"2023-10-05","cited_by_count":181},{"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":"2501.06598","title":"ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation","created":"2025-01-11","cited_by_count":92},{"id":"2206.06888","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","created":"2022-06-14","cited_by_count":87},{"id":"2103.00073","title":"CURE: Code-Aware Neural Machine Translation for Automatic Program Repair","created":"2021-02-26","cited_by_count":86},{"id":"2409.03733","title":"Planning In Natural Language Improves LLM Search For Code Generation","created":"2024-09-05","cited_by_count":83},{"id":"2304.06815","title":"Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)","created":"2023-04-13","cited_by_count":72},{"id":"2304.11384","title":"Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning","created":"2023-04-22","cited_by_count":72},{"id":"2308.11396","title":"Towards an Understanding of Large Language Models in Software Engineering Tasks","created":"2023-08-22","cited_by_count":68},{"id":"2311.10372","title":"A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends","created":"2023-11-17","cited_by_count":66},{"id":"2410.03981","title":"A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages","created":"2024-10-04","cited_by_count":66},{"id":"2303.09384","title":"LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations","created":"2023-03-16","cited_by_count":62},{"id":"2206.07585","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","created":"2022-06-15","cited_by_count":54},{"id":"2404.10100","title":"LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation","created":"2024-04-15","cited_by_count":49},{"id":"2205.12713","title":"jTrans: Jump-Aware Transformer for Binary Code Similarity","created":"2022-05-25","cited_by_count":44},{"id":"2401.07102","title":"Evolving Code with A Large Language Model","created":"2024-01-13","cited_by_count":43},{"id":"2105.12485","title":"TreeBERT: A Tree-Based Pre-Trained Model for Programming Language","created":"2021-05-26","cited_by_count":41},{"id":"2304.02195","title":"Explainable Automated Debugging via Large Language Model-driven Scientific Debugging","created":"2023-04-05","cited_by_count":40},{"id":"2311.00889","title":"SALLM: Security Assessment of Generated Code","created":"2023-11-01","cited_by_count":39},{"id":"2403.05286","title":"LLM4Decompile: Decompiling Binary Code with Large Language Models","created":"2024-03-08","cited_by_count":39},{"id":"2406.06025","title":"RepoQA: Evaluating Long Context Code Understanding","created":"2024-06-10","cited_by_count":35},{"id":"2402.13521","title":"Test-Driven Development for Code Generation","created":"2024-02-21","cited_by_count":34},{"id":"2312.04730","title":"DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructions","created":"2023-12-07","cited_by_count":33},{"id":"2308.14731","title":"Distilled GPT for Source Code Summarization","created":"2023-08-28","cited_by_count":31},{"id":"2407.07959","title":"Source Code Summarization in the Era of Large Language Models","created":"2024-07-09","cited_by_count":31},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30},{"id":"2302.00288","title":"CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models","created":"2023-02-01","cited_by_count":28},{"id":"2308.15276","title":"Large Language Models in Fault Localisation","created":"2023-08-29","cited_by_count":28},{"id":"2407.02395","title":"Toward Secure Code Generation: Bridging Correctness and Security via Task-Adaptive Vulnerability Modeling and Execution-Based Benchmarking","created":"2024-07-02","cited_by_count":27},{"id":"2310.06530","title":"Refining Decompiled C Code with Large Language Models","created":"2023-10-10","cited_by_count":24},{"id":"2312.10349","title":"A Comparative Analysis of Large Language Models for Code Documentation Generation","created":"2023-12-16","cited_by_count":24},{"id":"2410.18889","title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance","created":"2024-10-24","cited_by_count":20},{"id":"1909.11424","title":"A Survey of Binary Code Similarity","created":"2019-09-25","cited_by_count":19},{"id":"2109.02040","title":"Data Efficient Masked Language Modeling for Vision and Language","created":"2021-09-05","cited_by_count":19},{"id":"2411.02320","title":"An Empirical Study on the Code Refactoring Capability of Large Language Models","created":"2024-11-04","cited_by_count":19},{"id":"2408.05002","title":"An Empirical Study on Challenges for LLM Application Developers","created":"2024-08-06","cited_by_count":18},{"id":"2402.14182","title":"Do Machines and Humans Focus on Similar Code? Exploring Explainability of Large Language Models in Code Summarization","created":"2024-02-22","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":"2405.01103","title":"LLM Security Guard for Code","created":"2024-05-02","cited_by_count":15},{"id":"2306.05152","title":"Towards Autonomous Testing Agents via Conversational Large Language Models","created":"2023-06-08","cited_by_count":13},{"id":"2312.09601","title":"Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models","created":"2023-12-15","cited_by_count":13},{"id":"2109.04738","title":"On the validity of pre-trained transformers for natural language processing in the software engineering domain","created":"2021-09-10","cited_by_count":11},{"id":"2112.01218","title":"GraphCode2Vec: Generic Code Embedding via Lexical and Program Dependence Analyses","created":"2021-12-02","cited_by_count":11},{"id":"2311.10401","title":"LLM-based Control Code Generation using Image Recognition","created":"2023-11-17","cited_by_count":10},{"id":"2501.07849","title":"The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation","created":"2025-01-14","cited_by_count":10},{"id":"2408.04820","title":"Natural Language Outlines for Code: Literate Programming in the LLM Era","created":"2024-08-09","cited_by_count":9},{"id":"2405.19581","title":"Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases","created":"2024-05-30","cited_by_count":8},{"id":"2406.06637","title":"Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering","created":"2024-06-09","cited_by_count":8},{"id":"2407.01646","title":"ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization","created":"2024-07-01","cited_by_count":8},{"id":"2408.04477","title":"What You Need is What You Get: Theory of Mind for an LLM-Based Code Understanding Assistant","created":"2024-08-08","cited_by_count":8},{"id":"2407.08924","title":"Disassembling Obfuscated Executables with LLM","created":"2024-07-12","cited_by_count":7},{"id":"2410.21071","title":"Automatic Generation of Benchmarks and Reliable LLM Judgment for Code Tasks","created":"2024-10-28","cited_by_count":7},{"id":"2411.10129","title":"Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation","created":"2024-11-15","cited_by_count":7},{"id":"2401.05940","title":"Mutation-based Consistency Testing for Evaluating the Code Understanding Capability of LLMs","created":"2024-01-11","cited_by_count":6},{"id":"2308.07429","title":"Semantic Similarity Loss for Neural Source Code Summarization","created":"2023-08-14","cited_by_count":5},{"id":"2401.09885","title":"Source Code Clone Detection Using Unsupervised Similarity Measures","created":"2024-01-18","cited_by_count":5},{"id":"2406.11346","title":"WaDec: Decompiling WebAssembly Using Large Language Model","created":"2024-06-17","cited_by_count":5},{"id":"2410.06735","title":"Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?","created":"2024-10-09","cited_by_count":5},{"id":"2103.12778","title":"PSIMiner: A Tool for Mining Rich Abstract Syntax Trees from Code","created":"2021-03-23","cited_by_count":4},{"id":"2404.03114","title":"Testing the Effect of Code Documentation on Large Language Model Code Understanding","created":"2024-04-03","cited_by_count":4},{"id":"2408.03623","title":"Improving Retrieval-Augmented Code Comment Generation by Retrieving for Generation","created":"2024-08-07","cited_by_count":4},{"id":"2406.17233","title":"Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement","created":"2024-06-25","cited_by_count":3},{"id":"2408.07106","title":"\"You still have to study\" -- On the Security of LLM generated code","created":"2024-08-13","cited_by_count":3},{"id":"2410.14321","title":"From Solitary Directives to Interactive Encouragement! LLM Secure Code Generation by Natural Language Prompting","created":"2024-10-18","cited_by_count":3},{"id":"2411.07091","title":"Impact of LLM-based Review Comment Generation in Practice: A Mixed Open-/Closed-source User Study","created":"2024-11-11","cited_by_count":3},{"id":"2310.07109","title":"SparseCoder: Advancing Source Code Analysis with Sparse Attention and Learned Token Pruning","created":"2023-10-11","cited_by_count":2},{"id":"2408.06385","title":"ViC: Virtual Compiler Is All You Need For Assembly Code Search","created":"2024-08-10","cited_by_count":2},{"id":"2408.09735","title":"Icing on the Cake: Automatic Code Summarization at Ericsson","created":"2024-08-19","cited_by_count":2},{"id":"2411.06680","title":"Anchor Attention, Small Cache: Code Generation with Large Language Models","created":"2024-11-11","cited_by_count":2},{"id":"2501.00217","title":"The Potential of LLMs in Automating Software Testing: From Generation to Reporting","created":"2024-12-31","cited_by_count":2},{"id":"2501.05724","title":"I Can't Share Code, but I need Translation -- An Empirical Study on Code Translation through Federated LLM","created":"2025-01-10","cited_by_count":2},{"id":"2503.15270","title":"Automating Comment Generation for Smart Contract from Bytecode","created":"2025-03-19","cited_by_count":2}],"next_cursor":null}