Causal Direct Preference Optimization for Distributionally Robust Generative Rec

arXiv:2605.00327v1 Announce Type: cross Abstract: In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns

arXiv:2603.22829v1 Announce Type: new Abstract: With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted

arXiv:2610.00061v1 Announce Type: new Abstract: Personalizing large language models (LLMs) requires aligning generation behavior with user-specific preferences rather than

arXiv:2607.01715v1 Announce Type: new Abstract: Existing robust preference optimization for language-model alignment mainly studies pairwise supervision and places robustness at

arXiv:2605.19461v1 Announce Type: new Abstract: On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity,

arXiv:2605.08354v1 Announce Type: new Abstract: Aligning multimodal generative models with human preferences demands reward signals that respect the compositional,

arXiv:2603.18736v1 Announce Type: cross Abstract: Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models, current reward modeling

arXiv:2603.18258v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has emerged as a popular algorithm for aligning pretrained large language models with human