{"total":98,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2503.03480","title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","created":"2025-03-05","cited_by_count":72,"area":"vla"},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2403.17830","title":"Assessment of Multimodal Large Language Models in Alignment with Human Values","created":"2024-03-26","cited_by_count":36,"area":"mllm"},{"id":"2406.14477","title":"SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset","created":"2024-06-20","cited_by_count":35,"area":"alignment"},{"id":"2402.17887","title":"JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability","created":"2024-02-27","cited_by_count":32,"area":"lr"},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2503.17682","title":"Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback","created":"2025-03-22","cited_by_count":30,"area":"mllm"},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27,"area":"alignment"},{"id":"2502.11555","title":"Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models","created":"2025-02-17","cited_by_count":22,"area":"alignment"},{"id":"2506.10597","title":"SoK: Evaluating Jailbreak Guardrails for Large Language Models","created":"2025-06-12","cited_by_count":21,"area":"alignment"},{"id":"2503.04378","title":"HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks","created":"2025-03-06","cited_by_count":17,"area":"lr"},{"id":"2503.02877","title":"Weak-to-Strong Generalization Even in Random Feature Networks, Provably","created":"2025-03-04","cited_by_count":15,"area":null},{"id":"2502.01208","title":"On Almost Surely Safe Alignment of Large Language Models at Inference-Time","created":"2025-02-03","cited_by_count":14,"area":"alignment"},{"id":"2503.18130","title":"Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization","created":"2025-03-23","cited_by_count":14,"area":"alignment"},{"id":"2505.11063","title":"Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction","created":"2025-05-16","cited_by_count":14,"area":"lr"},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2502.18448","title":"Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing","created":"2025-02-25","cited_by_count":13,"area":null},{"id":"2505.20925","title":"Multi-objective Large Language Model Alignment with Hierarchical Experts","created":"2025-05-27","cited_by_count":13,"area":"alignment"},{"id":"2507.04756","title":"CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering","created":"2025-07-07","cited_by_count":13,"area":null},{"id":"2504.12663","title":"Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment","created":"2025-04-17","cited_by_count":11,"area":"alignment"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2402.10184","title":"Reward Generalization in RLHF: A Topological Perspective","created":"2024-02-15","cited_by_count":9,"area":"alignment"},{"id":"2409.00162","title":"Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback","created":"2024-08-30","cited_by_count":9,"area":"alignment"},{"id":"2506.06636","title":"SafeLawBench: Towards Safe Alignment of Large Language Models","created":"2025-06-07","cited_by_count":9,"area":"alignment"},{"id":"2509.08486","title":"Too Helpful, Too Harmless, Too Honest or Just Right?","created":"2025-09-10","cited_by_count":9,"area":"moe"},{"id":"2405.13578","title":"ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2405.18718","title":"Efficient Model-agnostic Alignment via Bayesian Persuasion","created":"2024-05-29","cited_by_count":8,"area":"alignment"},{"id":"2405.21040","title":"Direct Alignment of Language Models via Quality-Aware Self-Refinement","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2502.16770","title":"LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2505.20081","title":"Inference-time Alignment in Continuous Space","created":"2025-05-26","cited_by_count":7,"area":"alignment"},{"id":"2506.07434","title":"Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding","created":"2025-06-09","cited_by_count":7,"area":"alignment"},{"id":"2512.05485","title":"TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations","created":"2025-12-05","cited_by_count":7,"area":"safety"},{"id":"2406.18695","title":"Learning to Correct for QA Reasoning with Black-box LLMs","created":"2024-06-26","cited_by_count":6,"area":"lr"},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2506.00166","title":"Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment","created":"2025-05-30","cited_by_count":6,"area":"alignment"},{"id":"2601.10589","title":"Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay","created":"2026-01-15","cited_by_count":6,"area":"alignment"},{"id":"2503.04240","title":"DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models","created":"2025-03-06","cited_by_count":5,"area":"alignment"},{"id":"2503.11720","title":"RPO: Fine-Tuning Visual Generative Models via Rich Vision-Language Preferences","created":"2025-03-13","cited_by_count":5,"area":"diffusion"},{"id":"2507.12841","title":"AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2509.03348","title":"Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2512.23260","title":"Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation","created":"2025-12-29","cited_by_count":5,"area":"alignment"},{"id":"2505.23950","title":"InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback","created":"2025-05-29","cited_by_count":4,"area":"alignment"},{"id":"2508.05015","title":"SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning","created":"2025-08-07","cited_by_count":4,"area":"lr"},{"id":"2509.14651","title":"MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models","created":"2025-09-18","cited_by_count":4,"area":"safety"},{"id":"2509.16444","title":"Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2509.19358","title":"Benchmarking and Improving LLM Robustness for Personalized Generation","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2511.06778","title":"SAFENLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database Interfaces","created":"2025-11-10","cited_by_count":4,"area":"alignment"},{"id":"2506.07811","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2506.15717","title":"daDPO: Distribution-Aware DPO for Distilling Conversational Abilities","created":"2025-06-03","cited_by_count":3,"area":"alignment"},{"id":"2509.16779","title":"Improving User Interface Generation Models from Designer Feedback","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2509.22510","title":"We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2512.23067","title":"The Reward Model Selection Crisis in Personalized Alignment","created":"2025-12-28","cited_by_count":3,"area":"alignment"},{"id":"2605.05058","title":"SoK: Robustness in Large Language Models against Jailbreak Attacks","created":"2026-05-06","cited_by_count":3,"area":"safety"},{"id":"2406.10813","title":"Self-Evolution Fine-Tuning for Policy Optimization","created":"2024-06-16","cited_by_count":2,"area":"alignment"},{"id":"2501.05336","title":"Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction","created":"2025-01-09","cited_by_count":2,"area":"alignment"},{"id":"2504.17404","title":"Super Co-alignment of Human and AI for Sustainable Symbiotic Society","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2505.21191","title":"Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities","created":"2025-05-27","cited_by_count":2,"area":"moe"},{"id":"2506.20949","title":"Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation","created":"2025-06-26","cited_by_count":2,"area":"agents"},{"id":"2508.09016","title":"A Survey on Training-free Alignment of Large Language Models","created":"2025-08-12","cited_by_count":2,"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":"2511.16324","title":"SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning","created":"2025-11-20","cited_by_count":2,"area":"alignment"},{"id":"2512.15011","title":"Epistemic diversity across language models mitigates knowledge collapse","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2602.21215","title":"Inference-time Alignment via Sparse Junction Steering","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2604.19016","title":"AlignCultura: Towards Culturally Aligned Large Language Models?","created":"2026-04-21","cited_by_count":2,"area":"alignment"},{"id":"2605.04539","title":"RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization","created":"2026-05-06","cited_by_count":2,"area":"alignment"},{"id":"2605.05742","title":"Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2609.10439","title":"Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs","created":"2026-09-09","cited_by_count":2,"area":"safety"},{"id":"2609.26579","title":"Receptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models","created":"2026-09-22","cited_by_count":2,"area":null},{"id":"2410.03731","title":"Unsupervised Human Preference Learning","created":"2024-09-30","cited_by_count":1,"area":"lr"},{"id":"2505.19700","title":"Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2505.19743","title":"Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2508.04626","title":"P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis","created":"2025-08-06","cited_by_count":1,"area":"alignment"},{"id":"2510.11824","title":"Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.12044","title":"Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language Models","created":"2025-10-14","cited_by_count":1,"area":"alignment"},{"id":"2511.10210","title":"Advanced Black-Box Tuning of Large Language Models with Limited API Calls","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2602.07381","title":"When the Model Said 'No Comment', We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified","created":"2026-02-07","cited_by_count":1,"area":"moe"},{"id":"2603.28817","title":"GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models","created":"2026-03-28","cited_by_count":1,"area":"safety"},{"id":"2605.12908","title":"The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.02640","title":"D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting","created":"2026-05-31","cited_by_count":1,"area":"safety"},{"id":"2609.12373","title":"Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2404.17749","title":"UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt -- A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis","created":"2024-04-27","cited_by_count":0,"area":null},{"id":"2507.11502","title":"HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2508.01198","title":"Adaptive Content Restriction for Large Language Models via Suffix Optimization","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2508.09937","title":"A Comprehensive Evaluation framework of Alignment Techniques for LLMs","created":"2025-08-13","cited_by_count":0,"area":"alignment"},{"id":"2509.05605","title":"Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation","created":"2025-09-06","cited_by_count":0,"area":"alignment"},{"id":"2510.05703","title":"Provably Convergent Primal-Dual DPO for Constrained LLM Alignment","created":"2025-10-07","cited_by_count":0,"area":"alignment"},{"id":"2510.14398","title":"YNTP-100: A Benchmark for Your Next Token Prediction with 100 People","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2604.17210","title":"Guardrails in Logit Space: Safety Token Regularization for LLM Alignment","created":"2026-04-19","cited_by_count":0,"area":"alignment"},{"id":"2604.23543","title":"Pref-CTRL: Preference Driven LLM Alignment using Representation Editing","created":"2026-04-26","cited_by_count":0,"area":"alignment"},{"id":"2605.11712","title":"Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2605.25342","title":"MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2607.23175","title":"Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.00624","title":"Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.13624","title":"An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS","created":"2026-09-12","cited_by_count":0,"area":"safety"},{"id":"2610.05898","title":"Collaborative Personalized Preference Alignment for LLMs under Data Deficiency","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}