作者位次 #4/8SIGIR 2026Poster· Information Retrieval (Industry)
Breaking the Relevance–Diversity Seesaw: Hierarchical LLM Reasoning with RL for Industrial Novelty Recommendation
Ying Sun · Yanyan Zou · Xiao Wang · Hanchuan Xu · Xuanhua Yang · Sulong Xu · Junbo Qi · Shengjie Li
摘要
Novelty recommendation sustains long-term user engagement by exposing users to content that is both relevant and meaningfully different from their recent consumption. In large-scale e-commerce, this requires composing coherent yet non-redundant recommendation lists, a task fundamentally constrain...