{"total":36,"rows":[{"id":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244,"area":"alignment"},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"id":"2507.18624","title":"Checklists Are Better Than Reward Models For Aligning Language Models","created":"2025-07-24","cited_by_count":128,"area":"alignment"},{"id":"2505.11475","title":"HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages","created":"2025-05-16","cited_by_count":75,"area":"alignment"},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2409.13221","title":"Optimizing RLHF Training for Large Language Models with Stage Fusion","created":"2024-09-20","cited_by_count":43,"area":"alignment"},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"area":"alignment"},{"id":"2312.10584","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","created":"2023-12-17","cited_by_count":35,"area":"alignment"},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35,"area":"alignment"},{"id":"2506.05598","title":"SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs","created":"2025-06-05","cited_by_count":29,"area":"alignment"},{"id":"2410.19133","title":"Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback","created":"2024-10-24","cited_by_count":26,"area":"alignment"},{"id":"2504.07532","title":"AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation","created":"2025-04-10","cited_by_count":25,"area":"alignment"},{"id":"2406.10630","title":"Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models","created":"2024-06-15","cited_by_count":18,"area":"alignment"},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2404.00530","title":"Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization","created":"2024-03-31","cited_by_count":15,"area":"alignment"},{"id":"2502.04322","title":"Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions","created":"2025-02-06","cited_by_count":15,"area":"alignment"},{"id":"2410.04166","title":"Learning from negative feedback, or positive feedback or both","created":"2024-10-05","cited_by_count":13,"area":"alignment"},{"id":"2408.16961","title":"The Future of Open Human Feedback","created":"2024-08-15","cited_by_count":10,"area":"alignment"},{"id":"2507.13579","title":"Learning to summarize user information for personalized reinforcement learning from human feedback","created":"2025-07-17","cited_by_count":10,"area":"alignment"},{"id":"2506.16655","title":"Arch-Router: Aligning LLM Routing with Human Preferences","created":"2025-06-19","cited_by_count":9,"area":"alignment"},{"id":"2406.16783","title":"M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models","created":"2024-06-24","cited_by_count":7,"area":"alignment"},{"id":"2506.03968","title":"From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding","created":"2025-06-04","cited_by_count":5,"area":"alignment"},{"id":"2506.04180","title":"SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models","created":"2025-06-04","cited_by_count":5,"area":"alignment"},{"id":"2510.02341","title":"DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning","created":"2025-09-27","cited_by_count":5,"area":"alignment"},{"id":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","created":"2026-02-06","cited_by_count":3,"area":"alignment"},{"id":"2511.06512","title":"EASE: Practical and Efficient Safety Alignment for Small Language Models","created":"2025-11-09","cited_by_count":2,"area":"alignment"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2510.06670","title":"PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch","created":"2025-10-08","cited_by_count":1,"area":"alignment"},{"id":"2510.07557","title":"Investigating Thematic Patterns and User Preferences in LLM Interactions using BERTopic","created":"2025-10-08","cited_by_count":1,"area":"alignment"},{"id":"2607.14240","title":"Align AI to Dynamic Human-AI Workflows","created":"2026-07-15","cited_by_count":1,"area":"alignment"},{"id":"2602.04000","title":"After Talking with 1,000 Personas: Learning Preference-Aligned Proactive Assistants From Large-Scale Persona Interactions","created":"2026-02-03","cited_by_count":0,"area":"alignment"},{"id":"2604.27453","title":"From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2608.29936","title":"When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs","created":"2026-08-30","cited_by_count":0,"area":"alignment"},{"id":"2609.34033","title":"Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation","created":"2026-09-27","cited_by_count":0,"area":"alignment"}],"next_cursor":null}