{"total":53,"rows":[{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2404.08676","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","created":"2024-04-06","cited_by_count":98,"area":"safety"},{"id":"2509.14745","title":"On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub","created":"2025-09-18","cited_by_count":55,"area":"agents"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2402.15302","title":"How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries","created":"2024-02-23","cited_by_count":27,"area":"safety"},{"id":"2409.16430","title":"A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions","created":"2024-09-24","cited_by_count":27,"area":null},{"id":"2504.10147","title":"A Survey of Personalization: From RAG to Agent","created":"2025-04-14","cited_by_count":27,"area":"rag"},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2503.01245","title":"Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2503.17181","title":"A Study of LLMs' Preferences for Libraries and Programming Languages","created":"2025-03-21","cited_by_count":20,"area":null},{"id":"2402.18502","title":"Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification","created":"2024-02-28","cited_by_count":18,"area":null},{"id":"2407.13928","title":"BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization","created":"2024-07-18","cited_by_count":18,"area":"alignment"},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"id":"2510.07920","title":"Profit Mirage: Revisiting Information Leakage in LLM-based Financial Agents","created":"2025-10-09","cited_by_count":14,"area":"agents"},{"id":"2409.09464","title":"Measuring the Influence of Incorrect Code on Test Generation","created":"2024-09-14","cited_by_count":11,"area":null},{"id":"2408.04643","title":"Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2509.04373","title":"Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases","created":"2025-09-04","cited_by_count":8,"area":null},{"id":"2403.04931","title":"A Survey on Human-AI Collaboration with Large Foundation Models","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2505.23829","title":"BiasFilter: An Inference-Time Debiasing Framework for Large Language Models","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2501.11354","title":"Towards Advancing Code Generation with Large Language Models: A Research Roadmap","created":"2025-01-20","cited_by_count":5,"area":null},{"id":"2311.17228","title":"Survey on AI Ethics: A Socio-technical Perspective","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2511.01348","title":"The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2605.30777","title":"What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2509.08146","title":"Bias after Prompting: Persistent Discrimination in Large Language Models","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2602.20170","title":"CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2606.15453","title":"A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM Inference","created":"2026-06-13","cited_by_count":3,"area":"moe"},{"id":"2409.13843","title":"STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2501.13833","title":"On the Reasoning Capacity of AI Models and How to Quantify It","created":"2025-01-23","cited_by_count":2,"area":"lr"},{"id":"2505.15475","title":"LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2601.08833","title":"Revisiting Disaggregated Large Language Model Serving for Performance and Energy Implications","created":"2025-11-14","cited_by_count":2,"area":"inference"},{"id":"2604.05756","title":"Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2404.10508","title":"White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2506.15453","title":"Uncovering Intention through LLM-Driven Code Snippet Description Generation","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2507.23087","title":"On LLM-Assisted Generation of Smart Contracts from Business Processes","created":"2025-07-30","cited_by_count":1,"area":null},{"id":"2509.18137","title":"LoRALib: A Standardized Benchmark for Evaluating LoRA-MoE Methods","created":"2025-09-14","cited_by_count":1,"area":"moe"},{"id":"2510.18131","title":"BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2512.03943","title":"Is Lying Only Sinful in Islam? Exploring Religious Bias in Multilingual Large Language Models Across Major Religions","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2603.18019","title":"BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2605.00382","title":"Social Bias in LLM-Generated Code: Benchmark and Mitigation","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2606.24689","title":"Automated Summarization of Software Documents: An LLM-based Multi-Agent Approach","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2508.17735","title":"SMITE: Enhancing Fairness in LLMs through Optimal In-Context Example Selection via Dynamic Validation","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2510.03862","title":"Designing Empirical Studies on LLM-Based Code Generation: Towards a Reference Framework","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2512.00556","title":"Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2601.14528","title":"LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2604.13103","title":"Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review","created":"2026-04-10","cited_by_count":0,"area":"agents"},{"id":"2604.21716","title":"From If-Statements to ML Pipelines: Revisiting Bias in Code-Generation","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2608.03691","title":"Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.04336","title":"COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.06041","title":"LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.00248","title":"Authority Bias in Conversational Search Engines for Academic Paper Recommendation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.22102","title":"When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.26210","title":"Same Chart, Different Story: Bias in Vision-Language Chart Interpretation","created":"2026-08-12","cited_by_count":0,"area":"mllm"}],"next_cursor":null}