Category-Anchored Large Language Models for Next POI Recommendation
This work proposes ANCHOR, a category-anchored framework for semantic-to-entity grounding in next POI recommendation, which first estimates category-level mobility intent in a compact and stable semantic space, rather than predicting concrete POI entities directly.
Le-Xi Bai, Xiao-Peng Zeng, Xun Zhou et al.
· 0 citations