{"total":67,"rows":[{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"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":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2506.03517","title":"DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models","created":"2025-06-04","cited_by_count":34,"area":"diffusion"},{"id":"2502.17543","title":"Training a Generally Curious Agent","created":"2025-02-24","cited_by_count":31,"area":"agents"},{"id":"2505.18830","title":"On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization","created":"2025-05-24","cited_by_count":31,"area":"lr"},{"id":"2507.06187","title":"The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains","created":"2025-07-08","cited_by_count":28,"area":null},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2505.04560","title":"ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\\alpha$-$\\beta$-Divergence","created":"2025-05-07","cited_by_count":23,"area":"distill"},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2510.19422","title":"LLM Unlearning with LLM Beliefs","created":"2025-10-22","cited_by_count":17,"area":"safety"},{"id":"2512.04220","title":"On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement","created":"2025-12-03","cited_by_count":15,"area":"lr"},{"id":"2501.03884","title":"AlphaPO: Reward Shape Matters for LLM Alignment","created":"2025-01-07","cited_by_count":14,"area":"alignment"},{"id":"2505.05465","title":"ComPO: Preference Alignment via Comparison Oracles","created":"2025-05-08","cited_by_count":13,"area":"alignment"},{"id":"2509.24393","title":"Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2505.19770","title":"Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO","created":"2025-05-26","cited_by_count":10,"area":"alignment"},{"id":"2510.03669","title":"Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning","created":"2025-10-04","cited_by_count":10,"area":"lr"},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2602.04896","title":"Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models","created":"2026-02-03","cited_by_count":8,"area":"alignment"},{"id":"2602.18037","title":"Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards","created":"2026-02-20","cited_by_count":8,"area":"alignment"},{"id":"2508.06482","title":"Post-training for Efficient Communication via Convention Formation","created":"2025-08-08","cited_by_count":7,"area":null},{"id":"2505.02363","title":"SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning","created":"2025-05-05","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":"2507.08068","title":"Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions","created":"2025-07-10","cited_by_count":6,"area":"lr"},{"id":"2412.17696","title":"Understanding the Logic of Direct Preference Alignment through Logic","created":"2024-12-23","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2604.01723","title":"Causal Scene Narration with Runtime Safety Supervision for Vision-Language-Action Driving","created":"2026-04-02","cited_by_count":5,"area":"vla"},{"id":"2502.10505","title":"Preference learning made easy: Everything should be understood through win rate","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2505.12435","title":"SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment","created":"2025-05-18","cited_by_count":3,"area":"alignment"},{"id":"2510.20413","title":"Why DPO is a Misspecified Estimator and How to Fix It","created":"2025-10-23","cited_by_count":3,"area":"alignment"},{"id":"2605.08666","title":"The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2502.17507","title":"C2-DPO: Constrained Controlled Direct Preference Optimization","created":"2025-02-22","cited_by_count":2,"area":"alignment"},{"id":"2601.04670","title":"Learning Dynamics in RL Post-Training for Language Models","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2602.00603","title":"Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2602.00954","title":"Small-Margin Preferences Still Matter-If You Train Them Right","created":"2026-02-01","cited_by_count":2,"area":"alignment"},{"id":"2604.18239","title":"Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner","created":"2026-04-20","cited_by_count":2,"area":"alignment"},{"id":"2606.06667","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2502.05773","title":"PIPA: Preference Alignment as Prior-Informed Statistical Estimation","created":"2025-02-09","cited_by_count":1,"area":"alignment"},{"id":"2505.19964","title":"The Limits of Preference Data for Post-Training","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2505.23761","title":"Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2506.05260","title":"LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs","created":"2025-06-05","cited_by_count":1,"area":"alignment"},{"id":"2506.08616","title":"Generalizing while preserving monotonicity in comparison-based preference learning models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2603.18258","title":"Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization","created":"2026-03-18","cited_by_count":1,"area":"alignment"},{"id":"2603.22165","title":"ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric Constraints","created":"2026-03-23","cited_by_count":1,"area":"mllm"},{"id":"2604.04894","title":"Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2604.08723","title":"Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?","created":"2026-04-09","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"},{"id":"2607.16240","title":"Normalized Rewards for Preference Optimization","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2609.38987","title":"Smaller Models, Better Rejects: Preference Distillation Scaling","created":"2026-09-30","cited_by_count":1,"area":"distill"},{"id":"2505.23933","title":"BIRD: Behavior Induction via Representation-structure Distillation","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2506.08998","title":"On Monotonicity in AI Alignment","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2507.20133","title":"Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt Engineering","created":"2025-07-27","cited_by_count":0,"area":"alignment"},{"id":"2508.17225","title":"SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation","created":"2025-08-24","cited_by_count":0,"area":"rag"},{"id":"2602.06788","title":"Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences","created":"2026-02-06","cited_by_count":0,"area":"alignment"},{"id":"2603.24883","title":"Learning to Staff: Offline Reinforcement Learning and Fine-Tuned LLMs for Warehouse Staffing Optimization","created":"2026-03-25","cited_by_count":0,"area":"offlinerl"},{"id":"2605.23961","title":"Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2607.13430","title":"Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet","created":"2026-07-15","cited_by_count":0,"area":"alignment"},{"id":"2609.08634","title":"Suan: Rectifying Direct Preference Safety Alignment in Large Language Models","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2609.32445","title":"Masking Frequent Tokens Sharpens Direct Preference Optimization","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2609.40165","title":"PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01511","title":"GAW-PO: Preference Optimization with Gradient-Aligned Token Weights","created":"2026-10-01","cited_by_count":0,"area":"alignment"},{"id":"2610.19439","title":"Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}