{"total":196,"rows":[{"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":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115,"area":"alignment"},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97,"area":"alignment"},{"id":"2508.03686","title":"CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward","created":"2025-08-05","cited_by_count":40,"area":"alignment"},{"id":"2502.09650","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples","created":"2025-02-11","cited_by_count":37,"area":"alignment"},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2506.07520","title":"LeVo: High-Quality Song Generation with Multi-Preference Alignment","created":"2025-06-09","cited_by_count":25,"area":"alignment"},{"id":"2506.09996","title":"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring","created":"2025-06-11","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":"2508.10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation","created":"2025-08-14","cited_by_count":21,"area":"alignment"},{"id":"2502.09990","title":"X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability","created":"2025-02-14","cited_by_count":20,"area":"alignment"},{"id":"2503.18991","title":"Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment","created":"2025-03-23","cited_by_count":20,"area":"alignment"},{"id":"2506.16507","title":"Robust Reward Modeling via Causal Rubrics","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"id":"2507.00018","title":"Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections","created":"2025-06-15","cited_by_count":17,"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":"2507.14987","title":"AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning","created":"2025-07-20","cited_by_count":15,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2507.21183","title":"MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge","created":"2025-07-27","cited_by_count":15,"area":"alignment"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2511.07931","title":"SpeechJudge: Towards Human-Level Judgment for Speech Naturalness","created":"2025-11-11","cited_by_count":15,"area":"alignment"},{"id":"2502.11026","title":"RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment","created":"2025-02-16","cited_by_count":14,"area":"alignment"},{"id":"2509.07150","title":"PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design","created":"2025-09-08","cited_by_count":14,"area":"alignment"},{"id":"2510.26374","title":"BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning","created":"2025-10-30","cited_by_count":14,"area":"alignment"},{"id":"2505.10527","title":"WorldPM: Scaling Human Preference Modeling","created":"2025-05-15","cited_by_count":13,"area":"alignment"},{"id":"2506.12109","title":"Personalized LLM Decoding via Contrasting Personal Preference","created":"2025-06-13","cited_by_count":12,"area":"alignment"},{"id":"2510.15859","title":"InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training","created":"2025-10-17","cited_by_count":12,"area":"alignment"},{"id":"2501.16727","title":"xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking","created":"2025-01-28","cited_by_count":11,"area":"alignment"},{"id":"2502.01203","title":"KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity","created":"2025-02-03","cited_by_count":11,"area":"alignment"},{"id":"2505.17196","title":"Shape it Up! Restoring LLM Safety during Finetuning","created":"2025-05-22","cited_by_count":11,"area":"alignment"},{"id":"2506.15068","title":"Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation","created":"2025-06-18","cited_by_count":11,"area":"alignment"},{"id":"2509.19333","title":"Pluralistic Off-policy Evaluation and Alignment","created":"2025-09-15","cited_by_count":11,"area":"alignment"},{"id":"2510.23451","title":"Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences","created":"2025-10-27","cited_by_count":11,"area":"alignment"},{"id":"2505.11166","title":"SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization","created":"2025-05-16","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":"2512.16626","title":"Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game","created":"2025-12-18","cited_by_count":10,"area":"alignment"},{"id":"2604.02795","title":"Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks","created":"2026-04-03","cited_by_count":10,"area":"alignment"},{"id":"2503.16867","title":"ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering","created":"2025-03-21","cited_by_count":9,"area":"alignment"},{"id":"2506.10054","title":"Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs","created":"2025-06-11","cited_by_count":9,"area":"alignment"},{"id":"2603.08091","title":"Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization","created":"2026-03-09","cited_by_count":9,"area":"alignment"},{"id":"2504.14096","title":"VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment","created":"2025-04-18","cited_by_count":8,"area":"alignment"},{"id":"2507.11500","title":"ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning","created":"2025-07-14","cited_by_count":8,"area":"alignment"},{"id":"2509.15110","title":"TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference","created":"2025-09-18","cited_by_count":8,"area":"alignment"},{"id":"2601.01887","title":"Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance","created":"2026-01-05","cited_by_count":8,"area":"alignment"},{"id":"2508.14460","title":"DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization","created":"2025-08-20","cited_by_count":7,"area":"alignment"},{"id":"2511.20651","title":"RubricRL: Simple Generalizable Rewards for Text-to-Image Generation","created":"2025-11-25","cited_by_count":7,"area":"alignment"},{"id":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"area":"alignment"},{"id":"2603.00025","title":"TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation","created":"2026-02-03","cited_by_count":7,"area":"alignment"},{"id":"2604.07343","title":"Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization","created":"2026-04-08","cited_by_count":7,"area":"alignment"},{"id":"2502.00657","title":"LLM Safety Alignment is Divergence Estimation in Disguise","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6,"area":"alignment"},{"id":"2502.14619","title":"Reward Models Identify Consistency, Not Causality","created":"2025-02-20","cited_by_count":6,"area":"alignment"},{"id":"2502.17315","title":"HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization","created":"2025-02-24","cited_by_count":6,"area":"alignment"},{"id":"2503.04222","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","created":"2025-03-06","cited_by_count":6,"area":"alignment"},{"id":"2504.15843","title":"Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model","created":"2025-04-22","cited_by_count":6,"area":"alignment"},{"id":"2505.14185","title":"Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study","created":"2025-05-20","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":"2507.00665","title":"SAFER: Probing Safety in Reward Models with Sparse Autoencoder","created":"2025-07-01","cited_by_count":6,"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":"2509.06982","title":"CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention","created":"2025-09-01","cited_by_count":6,"area":"alignment"},{"id":"2510.04320","title":"Read the Scene, Not the Script: Outcome-Aware Safety for LLMs","created":"2025-10-05","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":"2502.03397","title":"SPRI: Aligning Large Language Models with Context-Situated Principles","created":"2025-02-05","cited_by_count":5,"area":"alignment"},{"id":"2506.02553","title":"Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective","created":"2025-06-03","cited_by_count":5,"area":"alignment"},{"id":"2507.17515","title":"URPO: A Unified Reward & Policy Optimization Framework for Large Language Models","created":"2025-07-23","cited_by_count":5,"area":"alignment"},{"id":"2508.02618","title":"Alleviating Attention Hacking in Discriminative Reward Modeling through Interaction Distillation","created":"2025-08-04","cited_by_count":5,"area":"alignment"},{"id":"2510.06915","title":"LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling","created":"2025-10-08","cited_by_count":5,"area":"alignment"},{"id":"2510.13694","title":"Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking","created":"2025-10-15","cited_by_count":5,"area":"alignment"},{"id":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2605.29156","title":"RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains","created":"2026-05-27","cited_by_count":5,"area":"alignment"},{"id":"2502.14560","title":"Less is More: Improving LLM Alignment via Preference Data Selection","created":"2025-02-20","cited_by_count":4,"area":"alignment"},{"id":"2503.10093","title":"Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling","created":"2025-03-13","cited_by_count":4,"area":"alignment"},{"id":"2505.11861","title":"Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity","created":"2025-05-17","cited_by_count":4,"area":"alignment"},{"id":"2505.13862","title":"PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks","created":"2025-05-20","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":"2506.05619","title":"Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2509.23765","title":"Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality","created":"2025-09-28","cited_by_count":4,"area":"alignment"},{"id":"2602.11523","title":"Unifying Stable Optimization and Reference Regularization in RLHF","created":"2026-02-12","cited_by_count":4,"area":"alignment"},{"id":"2603.09312","title":"IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework","created":"2026-03-10","cited_by_count":4,"area":"alignment"},{"id":"2605.16299","title":"ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization","created":"2026-04-17","cited_by_count":4,"area":"alignment"},{"id":"2605.26579","title":"Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards","created":"2026-05-26","cited_by_count":4,"area":"alignment"},{"id":"2502.01237","title":"The Differences Between Direct Alignment Algorithms are a Blur","created":"2025-02-03","cited_by_count":3,"area":"alignment"},{"id":"2506.01495","title":"C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2508.16982","title":"Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2509.17276","title":"Probabilistic Token Alignment for Large Language Model Fusion","created":"2025-09-21","cited_by_count":3,"area":"alignment"},{"id":"2509.23371","title":"Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization","created":"2025-09-27","cited_by_count":3,"area":"alignment"},{"id":"2509.23542","title":"On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2510.19325","title":"Balancing Rewards in Text Summarization: Multi-Objective Reinforcement Learning via HyperVolume Optimization","created":"2025-10-22","cited_by_count":3,"area":"alignment"},{"id":"2601.22801","title":"Clipping-Free Policy Optimization for Large Language Models","created":"2026-01-30","cited_by_count":3,"area":"alignment"},{"id":"2604.12710","title":"LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety","created":"2026-04-13","cited_by_count":3,"area":"alignment"},{"id":"2605.05750","title":"RVPO: Risk-Sensitive Alignment via Variance Regularization","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2605.18592","title":"AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning","created":"2026-05-18","cited_by_count":3,"area":"alignment"},{"id":"2605.25604","title":"DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning","created":"2026-05-25","cited_by_count":3,"area":"alignment"},{"id":"2607.21356","title":"Emergent Misalignment Recruits a Pre-existing Persona Subspace","created":"2026-07-23","cited_by_count":3,"area":"alignment"},{"id":"2502.14400","title":"HPS: Hard Preference Sampling for Human Preference Alignment","created":"2025-02-20","cited_by_count":2,"area":"alignment"},{"id":"2505.18799","title":"ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2506.19780","title":"Listwise Direct Preference Optimization with Multi-Dimensional Preference Mixing","created":"2025-06-24","cited_by_count":2,"area":"alignment"},{"id":"2508.14076","title":"PersRM-R1: Enhance Personalized Reward Modeling with Reinforcement Learning","created":"2025-08-12","cited_by_count":2,"area":"alignment"}],"next_cursor":"100"}