{"total":44,"rows":[{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057,"area":"alignment"},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"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":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133,"area":"alignment"},{"id":"2503.15477","title":"What Makes a Reward Model a Good Teacher? An Optimization Perspective","created":"2025-03-19","cited_by_count":73,"area":"alignment"},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2403.01304","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","created":"2024-03-02","cited_by_count":20,"area":"alignment"},{"id":"2412.05469","title":"Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization","created":"2024-12-06","cited_by_count":20,"area":"alignment"},{"id":"2408.16482","title":"Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning","created":"2024-08-29","cited_by_count":19,"area":"alignment"},{"id":"2502.17254","title":"REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective","created":"2025-02-24","cited_by_count":15,"area":"alignment"},{"id":"2409.02231","title":"SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration","created":"2024-09-03","cited_by_count":14,"area":"alignment"},{"id":"2402.16030","title":"Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration","created":"2024-02-25","cited_by_count":13,"area":"alignment"},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13,"area":"alignment"},{"id":"2406.14393","title":"Jailbreaking as a Reward Misspecification Problem","created":"2024-06-20","cited_by_count":11,"area":"alignment"},{"id":"2505.12050","title":"AdaBoN: Adaptive Best-of-N Alignment","created":"2025-05-17","cited_by_count":9,"area":"alignment"},{"id":"2507.03236","title":"On Jailbreaking Quantized Language Models Through Fault Injection Attacks","created":"2025-07-04","cited_by_count":8,"area":"alignment"},{"id":"2407.02987","title":"LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models","created":"2024-07-03","cited_by_count":7,"area":"alignment"},{"id":"2507.07981","title":"Why is Your Language Model a Poor Implicit Reward Model?","created":"2025-07-10","cited_by_count":6,"area":"alignment"},{"id":"2104.08765","title":"Improving Neural Model Performance through Natural Language Feedback on Their Explanations","created":"2021-04-18","cited_by_count":5,"area":"alignment"},{"id":"2404.16020","title":"Investigating Adversarial Trigger Transfer in Large Language Models","created":"2024-04-24","cited_by_count":5,"area":"alignment"},{"id":"2407.01470","title":"DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging","created":"2024-07-01","cited_by_count":5,"area":"alignment"},{"id":"2412.07192","title":"PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips","created":"2024-12-10","cited_by_count":5,"area":"alignment"},{"id":"2412.12583","title":"Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise","created":"2024-12-17","cited_by_count":5,"area":"alignment"},{"id":"2507.02332","title":"PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage","created":"2025-07-03","cited_by_count":5,"area":"alignment"},{"id":"2404.18410","title":"Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting","created":"2024-04-29","cited_by_count":4,"area":"alignment"},{"id":"2412.13998","title":"Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes","created":"2024-12-18","cited_by_count":4,"area":"alignment"},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","cited_by_count":4,"area":"alignment"},{"id":"2501.06164","title":"Model Alignment Search","created":"2025-01-10","cited_by_count":3,"area":"alignment"},{"id":"2510.12355","title":"Fine-grained Analysis of Brain-LLM Alignment through Input Attribution","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2603.16152","title":"HIPO: Instruction Hierarchy via Constrained Reinforcement Learning","created":"2026-03-17","cited_by_count":3,"area":"alignment"},{"id":"2604.08326","title":"ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection","created":"2026-04-09","cited_by_count":2,"area":"alignment"},{"id":"2606.09850","title":"Mechanistic Analysis of Alignment Algorithms in Language Models","created":"2026-05-09","cited_by_count":2,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2509.23667","title":"Why Alignment Must Precede Distillation: A Minimal Working Explanation","created":"2025-09-28","cited_by_count":1,"area":"alignment"},{"id":"2510.21090","title":"Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2512.06343","title":"When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models","created":"2025-12-06","cited_by_count":1,"area":"alignment"},{"id":"2604.25872","title":"When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient","created":"2026-04-28","cited_by_count":1,"area":"alignment"},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2605.21558","title":"From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2606.15517","title":"SHARD: Safe and Helpful Alignment via Self-Reframing Distillation","created":"2026-06-14","cited_by_count":0,"area":"alignment"},{"id":"2609.22256","title":"DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues","created":"2026-09-06","cited_by_count":0,"area":"alignment"}],"next_cursor":null}