{"total":57,"rows":[{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376,"area":"alignment"},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112,"area":"alignment"},{"id":"2502.06193","title":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","created":"2025-02-10","cited_by_count":67,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2409.10164","title":"Quantile Regression for Distributional Reward Models in RLHF","created":"2024-09-16","cited_by_count":60,"area":"alignment"},{"id":"2604.20087","title":"SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks","created":"2026-04-22","cited_by_count":55,"area":"agents"},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51,"area":null},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2409.14664","title":"Direct Judgement Preference Optimization","created":"2024-09-23","cited_by_count":33,"area":"alignment"},{"id":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"id":"2601.20913","title":"Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges","created":"2026-01-28","cited_by_count":24,"area":null},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2505.11613","title":"MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2410.18585","title":"Aligning CodeLLMs with Direct Preference Optimization","created":"2024-10-24","cited_by_count":9,"area":"alignment"},{"id":"2502.11656","title":"Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL","created":"2025-02-17","cited_by_count":9,"area":"lr"},{"id":"2506.13326","title":"VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation","created":"2025-06-16","cited_by_count":9,"area":null},{"id":"2510.24358","title":"Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation","created":"2025-10-28","cited_by_count":9,"area":"agents"},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2506.00569","title":"AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs","created":"2025-05-31","cited_by_count":8,"area":"alignment"},{"id":"2604.08178","title":"Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling","created":"2026-04-09","cited_by_count":8,"area":"agents"},{"id":"2504.04699","title":"R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation","created":"2025-04-07","cited_by_count":7,"area":"lr"},{"id":"2509.02492","title":"GRAM-R$^2$: Self-Training Generative Foundation Reward Models for Reward Reasoning","created":"2025-09-02","cited_by_count":7,"area":"alignment"},{"id":"2408.15565","title":"SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models","created":"2024-08-28","cited_by_count":6,"area":"lr"},{"id":"2502.06633","title":"Combining Large Language Models with Static Analyzers for Code Review Generation","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2602.07422","title":"Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model","created":"2026-02-07","cited_by_count":6,"area":"alignment"},{"id":"2501.13264","title":"OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation","created":"2025-01-22","cited_by_count":5,"area":"alignment"},{"id":"2505.11875","title":"J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge","created":"2025-05-17","cited_by_count":5,"area":"lr"},{"id":"2508.12358","title":"Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications","created":"2025-08-17","cited_by_count":5,"area":null},{"id":"2410.20305","title":"Accelerating Direct Preference Optimization with Prefix Sharing","created":"2024-10-27","cited_by_count":4,"area":"alignment"},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2503.12167","title":"PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2504.19730","title":"Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2603.00539","title":"Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement","created":"2026-02-28","cited_by_count":4,"area":null},{"id":"2605.27028","title":"Less is More: Early Stopping Rollout for On-Policy Distillation","created":"2026-05-26","cited_by_count":4,"area":"distill"},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2509.03647","title":"Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators","created":"2025-09-03","cited_by_count":3,"area":"alignment"},{"id":"2502.16529","title":"Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation","created":"2025-02-23","cited_by_count":2,"area":"rag"},{"id":"2510.12121","title":"Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2605.01046","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2506.04464","title":"Leveraging Reward Models for Guiding Code Review Comment Generation","created":"2025-06-04","cited_by_count":1,"area":"alignment"},{"id":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2606.17949","title":"RouteBalance: Fused Model Routing and Load Balancing for Heterogeneous LLM Serving","created":"2026-06-16","cited_by_count":1,"area":"inference"},{"id":"2412.17395","title":"WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2504.05535","title":"COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values","created":"2025-04-07","cited_by_count":0,"area":"alignment"},{"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":"2510.27565","title":"CodeAlignBench: Assessing Code Generation Models on Developer-Preferred Code Adjustments","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2512.20328","title":"Toward Explaining Large Language Models in Software Engineering Tasks","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.19665","title":"CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging","created":"2026-05-19","cited_by_count":0,"area":"alignment"},{"id":"2606.10953","title":"Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.28998","title":"Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"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}