{"total":65,"rows":[{"id":"2501.04003","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","created":"2025-01-07","cited_by_count":122,"area":"mllm"},{"id":"2302.05527","title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","created":"2023-02-10","cited_by_count":102,"area":null},{"id":"2210.14306","title":"Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming","created":"2022-10-25","cited_by_count":91,"area":null},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91,"area":null},{"id":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53,"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":"2402.16197","title":"Language Models for Code Completion: A Practical Evaluation","created":"2024-02-25","cited_by_count":39,"area":null},{"id":"2306.04930","title":"When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming","created":"2023-06-08","cited_by_count":25,"area":"alignment"},{"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":"2406.10710","title":"SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task","created":"2024-06-15","cited_by_count":19,"area":"synth"},{"id":"2410.20527","title":"CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming","created":"2024-10-27","cited_by_count":19,"area":null},{"id":"2310.14424","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","created":"2023-10-22","cited_by_count":18,"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":"2505.11080","title":"BLEUBERI: BLEU is a surprisingly effective reward for instruction following","created":"2025-05-16","cited_by_count":17,"area":"alignment"},{"id":"2303.09128","title":"Exploring Distributional Shifts in Large Language Models for Code Analysis","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2209.05948","title":"Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems","created":"2022-09-13","cited_by_count":13,"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":"2304.13840","title":"A Deep Learning Framework for Verilog Autocompletion Towards Design and Verification Automation","created":"2023-04-26","cited_by_count":10,"area":null},{"id":"2401.09964","title":"When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference","created":"2024-01-18","cited_by_count":10,"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":"2310.07856","title":"Assessing Evaluation Metrics for Neural Test Oracle Generation","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2307.00012","title":"FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair","created":"2023-06-21","cited_by_count":6,"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":"2504.13472","title":"CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation","created":"2025-04-18","cited_by_count":6,"area":"agents"},{"id":"2506.11059","title":"CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2210.04802","title":"SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models","created":"2022-10-10","cited_by_count":5,"area":null},{"id":"2405.14753","title":"A Transformer-Based Approach for Smart Invocation of Automatic Code Completion","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2505.23932","title":"SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2506.10204","title":"Code Roulette: How Prompt Variability Affects LLM Code Generation","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2508.08236","title":"Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge","created":"2025-08-11","cited_by_count":4,"area":"alignment"},{"id":"2508.19558","title":"Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking","created":"2025-08-27","cited_by_count":4,"area":"synth"},{"id":"2408.03047","title":"OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents","created":"2024-08-06","cited_by_count":3,"area":"agents"},{"id":"2501.11006","title":"GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation","created":"2025-01-19","cited_by_count":3,"area":null},{"id":"2502.07835","title":"Bridging LLM-Generated Code and Requirements: Reverse Generation technique and SBC Metric for Developer Insights","created":"2025-02-11","cited_by_count":3,"area":null},{"id":"2508.13975","title":"ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation","created":"2025-08-19","cited_by_count":3,"area":null},{"id":"2609.04061","title":"When Models Edit Too Much: On the Fidelity of Minimal Code Edits","created":"2026-09-03","cited_by_count":3,"area":null},{"id":"2404.09249","title":"Test Code Generation for Telecom Software Systems using Two-Stage Generative Model","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2405.10243","title":"DocuMint: Docstring Generation for Python using Small Language Models","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2502.20175","title":"An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs","created":"2025-02-27","cited_by_count":2,"area":"lr"},{"id":"2504.04351","title":"DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation","created":"2025-04-06","cited_by_count":2,"area":"diffusion"},{"id":"2508.14288","title":"Measuring LLM Code Generation Stability via Structural Entropy","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2509.25043","title":"Large Language Models for Software Testing: A Research Roadmap","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.05788","title":"Mellum: Production-Grade in-IDE Contextual Code Completion with Multi-File Project Understanding","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2312.08976","title":"Dynamic Retrieval-Augmented Generation","created":"2023-12-14","cited_by_count":1,"area":"rag"},{"id":"2408.05026","title":"Retrieval-augmented code completion for local projects using large language models","created":"2024-08-09","cited_by_count":1,"area":"rag"},{"id":"2505.19442","title":"Style2Code: A Style-Controllable Code Generation Framework with Dual-Modal Contrastive Representation Learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2508.10161","title":"LaajMeter: A Framework for LaaJ Evaluation","created":"2025-08-13","cited_by_count":1,"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":"2605.05282","title":"Beyond BLEU: A Semantic Evaluation Method for Code Translation","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2503.21360","title":"From User Preferences to Optimization Constraints Using Large Language Models","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2504.12365","title":"Themisto: Jupyter-Based Runtime Benchmark","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2509.20172","title":"Benchmarking Web API Integration Code Generation","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.04349","title":"Challenge on Optimization of Context Collection for Code Completion","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2511.20656","title":"Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support","created":"2025-10-10","cited_by_count":0,"area":"agents"},{"id":"2601.17604","title":"Human-Aligned Enhancement of Programming Answers with LLMs Guided by User Feedback","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2605.24344","title":"Distinguishing Right from Wrong in Debates: Attribution Analysis of Chinese Harmful Memes","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.30819","title":"AI-Generated PowerShell Malware: An Experimental Framework and Dataset","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.06713","title":"Reliable and Developer-Aligned Evaluation of Agents for Software Engineering","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2608.17515","title":"Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related Task","created":"2026-08-18","cited_by_count":0,"area":"distill"},{"id":"2609.26749","title":"Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}