{"total":70,"rows":[{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637,"area":null},{"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,"area":null},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2302.06527","title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","created":"2023-02-13","cited_by_count":194,"area":null},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138,"area":null},{"id":"2206.07585","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","created":"2022-06-15","cited_by_count":54,"area":null},{"id":"2208.05446","title":"CoditT5: Pretraining for Source Code and Natural Language Editing","created":"2022-08-10","cited_by_count":45,"area":null},{"id":"2112.02043","title":"Multilingual training for Software Engineering","created":"2021-12-03","cited_by_count":43,"area":null},{"id":"2207.11680","title":"No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence","created":"2022-07-24","cited_by_count":41,"area":null},{"id":"2206.01335","title":"Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Code","created":"2022-06-02","cited_by_count":39,"area":null},{"id":"2402.07844","title":"Mercury: A Code Efficiency Benchmark for Code Large Language Models","created":"2024-02-12","cited_by_count":35,"area":null},{"id":"2308.04451","title":"Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks","created":"2023-08-04","cited_by_count":33,"area":"safety"},{"id":"2405.01745","title":"Large Language Models for UAVs: Current State and Pathways to the Future","created":"2024-05-02","cited_by_count":33,"area":null},{"id":"2204.09653","title":"On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages","created":"2022-04-05","cited_by_count":30,"area":null},{"id":"2112.02268","title":"Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding","created":"2021-12-04","cited_by_count":28,"area":null},{"id":"2406.16386","title":"Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach","created":"2024-06-24","cited_by_count":24,"area":null},{"id":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2205.11739","title":"Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code","created":"2022-05-24","cited_by_count":21,"area":null},{"id":"2302.04030","title":"CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models","created":"2023-02-08","cited_by_count":16,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2202.01142","title":"Pop Quiz! Can a Large Language Model Help With Reverse Engineering?","created":"2022-02-02","cited_by_count":14,"area":null},{"id":"2202.08029","title":"Code Search based on Context-aware Code Translation","created":"2022-02-16","cited_by_count":14,"area":null},{"id":"2306.01220","title":"Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2308.12415","title":"Benchmarking Causal Study to Interpret Large Language Models for Source Code","created":"2023-08-23","cited_by_count":14,"area":null},{"id":"2210.17040","title":"CodeEditor: Learning to Edit Source Code with Pre-trained Models","created":"2022-10-31","cited_by_count":12,"area":null},{"id":"2302.03788","title":"Toward a Theory of Causation for Interpreting Neural Code Models","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2408.11710","title":"Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests","created":"2024-08-21","cited_by_count":11,"area":null},{"id":"2409.06741","title":"Generative AI for Requirements Engineering: A Systematic Literature Review","created":"2024-09-10","cited_by_count":11,"area":null},{"id":"2409.08692","title":"B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests","created":"2024-09-13","cited_by_count":9,"area":null},{"id":"2104.14671","title":"SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics","created":"2021-04-29","cited_by_count":8,"area":null},{"id":"2302.04048","title":"Automating Code-Related Tasks Through Transformers: The Impact of Pre-training","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2310.07856","title":"Assessing Evaluation Metrics for Neural Test Oracle Generation","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2105.05991","title":"Improving Code Autocompletion with Transfer Learning","created":"2021-05-12","cited_by_count":6,"area":null},{"id":"2106.08415","title":"Code to Comment Translation: A Comparative Study on Model Effectiveness & Errors","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2403.06675","title":"Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code","created":"2024-03-11","cited_by_count":6,"area":"safety"},{"id":"2407.17053","title":"Automated Code-centric Software Vulnerability Assessment: How Far Are We? An Empirical Study in C/C++","created":"2024-07-24","cited_by_count":6,"area":null},{"id":"2206.00804","title":"Learning code summarization from a small and local dataset","created":"2022-06-02","cited_by_count":5,"area":null},{"id":"2305.12534","title":"BertRLFuzzer: A BERT and Reinforcement Learning Based Fuzzer","created":"2023-05-21","cited_by_count":5,"area":null},{"id":"2308.07429","title":"Semantic Similarity Loss for Neural Source Code Summarization","created":"2023-08-14","cited_by_count":5,"area":null},{"id":"2309.10264","title":"Revisiting and Improving Retrieval-Augmented Deep Assertion Generation","created":"2023-09-19","cited_by_count":5,"area":"rag"},{"id":"2210.03003","title":"MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentation","created":"2022-10-06","cited_by_count":4,"area":null},{"id":"2309.13218","title":"Language Models for Business Optimisation with a Real World Case Study in Production Scheduling","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2403.06485","title":"Knowledge-aware Alert Aggregation in Large-scale Cloud Systems: a Hybrid Approach","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2502.16071","title":"Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models","created":"2025-02-22","cited_by_count":4,"area":"rag"},{"id":"2506.02490","title":"Simplifying Root Cause Analysis in Kubernetes with StateGraph and LLM","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2202.04847","title":"A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2306.05079","title":"Enhancing Robustness of AI Offensive Code Generators via Data Augmentation","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2407.05202","title":"Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing","created":"2024-07-06","cited_by_count":3,"area":null},{"id":"2408.02402","title":"Enhancing AI-based Generation of Software Exploits with Contextual Information","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2411.02462","title":"Parameter-Efficient Fine-Tuning of Large Language Models for Unit Test Generation: An Empirical Study","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2303.07104","title":"xASTNN: Improved Code Representations for Industrial Practice","created":"2023-03-13","cited_by_count":2,"area":null},{"id":"2306.06620","title":"ARIST: An Effective API Argument Recommendation Approach","created":"2023-06-11","cited_by_count":2,"area":null},{"id":"2403.17357","title":"MESIA: Understanding and Leveraging Supplementary Nature of Method-level Comments for Automatic Comment Generation","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2502.10696","title":"Improving Retrieval-Augmented Deep Assertion Generation via Joint Training","created":"2025-02-15","cited_by_count":2,"area":"rag"},{"id":"2504.15989","title":"Optimizing Token Consumption in LLMs: A Nano Surge Approach for Code Reasoning Efficiency","created":"2025-04-22","cited_by_count":2,"area":"lr"},{"id":"2505.14838","title":"In-depth Research Impact Summarization through Fine-Grained Temporal Citation Analysis","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2307.02443","title":"An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2308.08943","title":"Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2402.16790","title":"Beyond Self-learned Attention: Mitigating Attention Bias in Transformer-based Models Using Attention Guidance","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2406.05364","title":"Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models","created":"2024-06-08","cited_by_count":1,"area":"safety"},{"id":"2510.03480","title":"LLM Agents for Automated Dependency Upgrades","created":"2025-10-03","cited_by_count":1,"area":"agents"},{"id":"2608.11965","title":"Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2209.10106","title":"Extreme Multi-Domain, Multi-Task Learning With Unified Text-to-Text Transfer Transformers","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2212.12584","title":"Neural Transition-based Parsing of Library Deprecations","created":"2022-12-23","cited_by_count":0,"area":null},{"id":"2412.13467","title":"Transducer Tuning: Efficient Model Adaptation for Software Tasks Using Code Property Graphs","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2505.14759","title":"LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2508.10311","title":"From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2601.21070","title":"Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2601.23059","title":"On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Study","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.12146","title":"Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning","created":"2026-02-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}