{"total":114,"rows":[{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431,"area":"alignment"},{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"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":"2402.13228","title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","created":"2024-02-20","cited_by_count":241,"area":"alignment"},{"id":"2311.08692","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","created":"2023-11-15","cited_by_count":145,"area":"alignment"},{"id":"2405.08448","title":"Understanding the performance gap between online and offline alignment algorithms","created":"2024-05-14","cited_by_count":110,"area":"alignment"},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95,"area":"alignment"},{"id":"2401.11206","title":"InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance","created":"2024-01-20","cited_by_count":83,"area":"alignment"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2404.12038","title":"Uncovering Safety Risks of Large Language Models through Concept Activation Vector","created":"2024-04-18","cited_by_count":67,"area":"alignment"},{"id":"2409.19817","title":"Calibrating Language Models with Adaptive Temperature Scaling","created":"2024-09-29","cited_by_count":58,"area":"alignment"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2402.12366","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","created":"2024-02-19","cited_by_count":36,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","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":"2405.20653","title":"Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries","created":"2024-05-31","cited_by_count":28,"area":"alignment"},{"id":"2403.11124","title":"Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment","created":"2024-03-17","cited_by_count":26,"area":"alignment"},{"id":"2404.00934","title":"ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback","created":"2024-04-01","cited_by_count":25,"area":"alignment"},{"id":"2406.07327","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","created":"2024-06-11","cited_by_count":24,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"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":"2412.05210","title":"Evaluating and Aligning CodeLLMs on Human Preference","created":"2024-12-06","cited_by_count":22,"area":"alignment"},{"id":"2406.15567","title":"SAIL: Self-Improving Efficient Online Alignment of Large Language Models","created":"2024-06-21","cited_by_count":20,"area":"alignment"},{"id":"2506.05346","title":"Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets","created":"2025-06-05","cited_by_count":20,"area":"alignment"},{"id":"2406.13925","title":"GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models","created":"2024-06-20","cited_by_count":18,"area":"alignment"},{"id":"2402.11296","title":"Dissecting Human and LLM Preferences","created":"2024-02-17","cited_by_count":17,"area":"alignment"},{"id":"2406.09920","title":"Knowledge Editing in Language Models via Adapted Direct Preference Optimization","created":"2024-06-14","cited_by_count":17,"area":"alignment"},{"id":"2504.13122","title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models","created":"2025-04-17","cited_by_count":17,"area":"alignment"},{"id":"2505.09558","title":"WavReward: Spoken Dialogue Models With Generalist Reward Evaluators","created":"2025-05-14","cited_by_count":15,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2402.16567","title":"Aligning Large Language Models to a Domain-specific Graph Database for NL2GQL","created":"2024-02-26","cited_by_count":14,"area":"alignment"},{"id":"2504.15804","title":"Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback","created":"2025-04-22","cited_by_count":14,"area":"alignment"},{"id":"2407.03038","title":"Towards Federated RLHF with Aggregated Client Preference for LLMs","created":"2024-07-03","cited_by_count":13,"area":"alignment"},{"id":"2505.10527","title":"WorldPM: Scaling Human Preference Modeling","created":"2025-05-15","cited_by_count":13,"area":"alignment"},{"id":"2412.01253","title":"Yi-Lightning Technical Report","created":"2024-12-02","cited_by_count":12,"area":"alignment"},{"id":"2403.03419","title":"Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization","created":"2024-03-06","cited_by_count":11,"area":"alignment"},{"id":"2412.15623","title":"JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs","created":"2024-12-20","cited_by_count":11,"area":"alignment"},{"id":"2501.04561","title":"OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis","created":"2025-01-08","cited_by_count":10,"area":"alignment"},{"id":"2503.02783","title":"Teaching Your Models to Understand Code via Focal Preference Alignment","created":"2025-03-04","cited_by_count":10,"area":"alignment"},{"id":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"area":"alignment"},{"id":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","cited_by_count":10,"area":"alignment"},{"id":"2511.19268","title":"BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment","created":"2025-11-24","cited_by_count":10,"area":"alignment"},{"id":"2401.05695","title":"Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback","created":"2024-01-11","cited_by_count":9,"area":"alignment"},{"id":"2406.01514","title":"Decoupled Alignment for Robust Plug-and-Play Adaptation","created":"2024-06-03","cited_by_count":9,"area":"alignment"},{"id":"2406.18118","title":"SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance","created":"2024-06-26","cited_by_count":9,"area":"alignment"},{"id":"2410.18585","title":"Aligning CodeLLMs with Direct Preference Optimization","created":"2024-10-24","cited_by_count":9,"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":"2503.06646","title":"Evaluating and Aligning Human Economic Risk Preferences in LLMs","created":"2025-03-09","cited_by_count":8,"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":"2410.11677","title":"Understanding Likelihood Over-optimisation in Direct Alignment Algorithms","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2410.23726","title":"Towards Reliable Alignment: Uncertainty-aware RLHF","created":"2024-10-31","cited_by_count":7,"area":"alignment"},{"id":"2412.03253","title":"Alignment at Pre-training! Towards Native Alignment for Arabic LLMs","created":"2024-12-04","cited_by_count":7,"area":"alignment"},{"id":"2504.10045","title":"CHARM: Calibrating Reward Models With Chatbot Arena Scores","created":"2025-04-14","cited_by_count":7,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"id":"2509.18632","title":"A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users","created":"2025-09-23","cited_by_count":6,"area":"alignment"},{"id":"2510.08697","title":"BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution","created":"2025-10-09","cited_by_count":6,"area":"alignment"},{"id":"2602.07892","title":"Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection","created":"2026-02-08","cited_by_count":6,"area":"alignment"},{"id":"2405.20053","title":"Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads","created":"2024-05-30","cited_by_count":5,"area":"alignment"},{"id":"2406.07971","title":"It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2406.08124","title":"Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2408.09834","title":"Minor DPO reject penalty to increase training robustness","created":"2024-08-19","cited_by_count":5,"area":"alignment"},{"id":"2412.17696","title":"Understanding the Logic of Direct Preference Alignment through Logic","created":"2024-12-23","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":"2406.10307","title":"What is the best model? Application-driven Evaluation for Large Language Models","created":"2024-06-14","cited_by_count":4,"area":"alignment"},{"id":"2505.03059","title":"Improving Model Alignment Through Collective Intelligence of Open-Source LLMS","created":"2025-05-05","cited_by_count":4,"area":"alignment"},{"id":"2506.05070","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2506.16078","title":"Probing the Robustness of Large Language Models Safety to Latent Perturbations","created":"2025-06-19","cited_by_count":4,"area":"alignment"},{"id":"2602.07340","title":"Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control","created":"2026-02-07","cited_by_count":4,"area":"alignment"},{"id":"2407.09447","title":"ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts","created":"2024-07-12","cited_by_count":3,"area":"alignment"},{"id":"2408.12579","title":"RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment","created":"2024-08-22","cited_by_count":3,"area":"alignment"},{"id":"2508.08550","title":"Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization","created":"2025-08-12","cited_by_count":3,"area":"alignment"},{"id":"2509.19360","title":"Semantic Representation Attack against Aligned Large Language Models","created":"2025-09-18","cited_by_count":3,"area":"alignment"},{"id":"2510.21190","title":"The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning","created":"2025-10-24","cited_by_count":3,"area":"alignment"},{"id":"2511.20604","title":"On Evaluating LLM Alignment by Evaluating LLMs as Judges","created":"2025-11-25","cited_by_count":3,"area":"alignment"},{"id":"2406.10813","title":"Self-Evolution Fine-Tuning for Policy Optimization","created":"2024-06-16","cited_by_count":2,"area":"alignment"},{"id":"2410.18127","title":"Holistic Utility Preference Learning for Listwise Alignment","created":"2024-10-17","cited_by_count":2,"area":"alignment"},{"id":"2503.03122","title":"The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models","created":"2025-03-05","cited_by_count":2,"area":"alignment"},{"id":"2504.05050","title":"Revealing the Intrinsic Ethical Vulnerability of Aligned Large Language Models","created":"2025-04-07","cited_by_count":2,"area":"alignment"},{"id":"2504.20520","title":"PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrations","created":"2025-04-29","cited_by_count":2,"area":"alignment"},{"id":"2509.17116","title":"MCTS-EP: Empowering Embodied Planning with Online Preference Optimization","created":"2025-09-21","cited_by_count":2,"area":"alignment"},{"id":"2601.14037","title":"Human detectors are surprisingly powerful reward models","created":"2026-01-15","cited_by_count":2,"area":"alignment"},{"id":"2602.01685","title":"Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment","created":"2026-02-02","cited_by_count":2,"area":"alignment"},{"id":"2604.24953","title":"ViPO: Visual Preference Optimization at Scale","created":"2026-04-27","cited_by_count":2,"area":"alignment"},{"id":"2606.02995","title":"Patcher: Post-Hoc Patching of Backdoored Large Language Models","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2406.19644","title":"Beyond Human Preferences: Exploring Reinforcement Learning Trajectory Evaluation and Improvement through LLMs","created":"2024-06-28","cited_by_count":1,"area":"alignment"},{"id":"2410.04112","title":"Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment","created":"2024-10-05","cited_by_count":1,"area":"alignment"},{"id":"2411.00897","title":"Enhancing the Traditional Chinese Medicine Capabilities of Large Language Model through Reinforcement Learning from AI Feedback","created":"2024-11-01","cited_by_count":1,"area":"alignment"},{"id":"2506.17828","title":"Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach","created":"2025-06-21","cited_by_count":1,"area":"alignment"},{"id":"2602.16802","title":"References Improve LLM Alignment in Non-Verifiable Domains","created":"2026-02-18","cited_by_count":1,"area":"alignment"},{"id":"2602.20676","title":"PRECTR-V2:Unified Relevance-CTR Framework with Cross-User Preference Mining, Exposure Bias Correction, and LLM-Distilled Encoder Optimization","created":"2026-02-24","cited_by_count":1,"area":"alignment"},{"id":"2604.04497","title":"One Model for All: Multi-Objective Controllable Language Models","created":"2026-04-06","cited_by_count":1,"area":"alignment"},{"id":"2605.02626","title":"Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models","created":"2026-05-04","cited_by_count":1,"area":"alignment"}],"next_cursor":"100"}