{"total":45,"rows":[{"id":"2206.15331","title":"GitHub Copilot AI pair programmer: Asset or Liability?","created":"2022-06-30","cited_by_count":152,"area":null},{"id":"2208.03133","title":"Out of the BLEU: how should we assess quality of the Code Generation models?","created":"2022-08-05","cited_by_count":65,"area":null},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57,"area":null},{"id":"2304.14317","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","created":"2023-04-27","cited_by_count":52,"area":null},{"id":"2410.02184","title":"CodeJudge: Evaluating Code Generation with Large Language Models","created":"2024-10-03","cited_by_count":44,"area":null},{"id":"2310.10628","title":"Data Contamination Through the Lens of Time","created":"2023-10-16","cited_by_count":40,"area":null},{"id":"2410.03131","title":"Code Comprehension then Auditing for Unsupervised LLM Evaluation","created":"2024-10-04","cited_by_count":32,"area":null},{"id":"2410.04194","title":"Consistent Autoformalization for Constructing Mathematical Libraries","created":"2024-10-05","cited_by_count":21,"area":null},{"id":"2406.12655","title":"Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2405.04520","title":"NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts","created":"2024-05-07","cited_by_count":19,"area":null},{"id":"2505.16222","title":"Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","created":"2025-05-22","cited_by_count":18,"area":null},{"id":"2104.13100","title":"Shellcode_IA32: A Dataset for Automatic Shellcode Generation","created":"2021-04-27","cited_by_count":16,"area":null},{"id":"2212.08950","title":"Beyond the C: Retargetable Decompilation using Neural Machine Translation","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2212.06008","title":"Who Evaluates the Evaluators? On Automatic Metrics for Assessing AI-based Offensive Code Generators","created":"2022-12-12","cited_by_count":11,"area":null},{"id":"2409.15204","title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","created":"2024-09-23","cited_by_count":10,"area":null},{"id":"2105.03317","title":"Toward Code Generation: A Survey and Lessons from Semantic Parsing","created":"2021-04-26","cited_by_count":8,"area":null},{"id":"2409.19801","title":"CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells","created":"2024-09-29","cited_by_count":8,"area":null},{"id":"2103.02523","title":"NeurIPS 2020 NLC2CMD Competition: Translating Natural Language to Bash Commands","created":"2021-03-03","cited_by_count":7,"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":"2310.18834","title":"Automating the Correctness Assessment of AI-generated Code for Security Contexts","created":"2023-10-28","cited_by_count":6,"area":null},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2409.00571","title":"Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairs","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2302.07845","title":"NL2CMD: An Updated Workflow for Natural Language to Bash Commands Translation","created":"2023-02-15","cited_by_count":3,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2502.18726","title":"Deep-Bench: Deep Learning Benchmark Dataset for Code Generation","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2203.15319","title":"Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation","created":"2022-03-29","cited_by_count":2,"area":null},{"id":"2312.09672","title":"InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2407.10626","title":"NoviCode: Generating Programs from Natural Language Utterances by Novices","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2501.04811","title":"Fast, Fine-Grained Equivalence Checking for Neural Decompilers","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2508.14288","title":"Measuring LLM Code Generation Stability via Structural Entropy","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2510.14115","title":"David vs. Goliath: A comparative study of different-sized LLMs for code generation in the domain of automotive scenario generation","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2510.23169","title":"MATCH: Task-Driven Code Evaluation through Contrastive Learning","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2511.15204","title":"Physics-Based Benchmarking Metrics for Multimodal Synthetic Images","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2511.22769","title":"Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2512.20159","title":"Benchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2605.05282","title":"Beyond BLEU: A Semantic Evaluation Method for Code Translation","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2202.03755","title":"Can We Generate Shellcodes via Natural Language? An Empirical Study","created":"2022-02-08","cited_by_count":0,"area":null},{"id":"2310.15015","title":"Leveraging Deep Learning for Abstractive Code Summarization of Unofficial Documentation","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2412.07538","title":"Can Neural Decompilation Assist Vulnerability Prediction on Binary Code?","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2510.09898","title":"Learning Bug Context for PyTorch-to-JAX Translation with LLMs","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.21537","title":"Excision Score: Evaluating Edits with Surgical Precision","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2512.00134","title":"Asm2SrcEval: Evaluating Large Language Models for Assembly-to-Source Code Translation","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2601.20909","title":"Leveraging Generative AI for Enhancing Domain-Driven Software Design","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2604.25778","title":"Can Code Evaluation Metrics Detect Code Plagiarism?","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2608.07038","title":"Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}