Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation 事件

Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation arXiv:2603.22335v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference alignment loss. However, our systematic empirical research and theoretical analysis reveal that DPO tends to amplify spurious correlations caused by environmental confound