Tmall Group of Alibaba)

The integration of Large Language Models (LLMs) into recommender systems has introduced a powerful paradigm for personalized recommedation. However, due to biases stemming from sensitive user attributes (e.g., gender, age), LLMs may generate discriminatory and unfair recommendations, even for use...

Post-click conversion rate (CVR) is a crucial element in online recommendation systems, which addresses significant challenges such as data sparsity (DS), sample selection bias (SSB), and delayed feedback. However, the impact of item discount rate-a key factor influencing both pricing and user pu...

Pre-ranking is a critical stage in large-scale recommendation systems, strictly demanding both high efficiency and effectiveness. Despite being the industry benchmark for pre-ranking owing to its serving efficiency, the two-tower structure, by virtue of its decoupled architecture, inherently rest...

Sequential recommendation models predominantly interpret user interactions as positive signals for preference accumulation. However, in e-commerce scenarios, a purchase action often signifies the termination of a specific intent (''Interest Exit'') rather than its continuation. Existing models ov...