Soyoung Park

Reliable relevance modeling and ranking are pivotal to legal information retrieval (IR), where graded relevance judgments are indispensable yet prohibitively expensive to acquire. Despite their importance, expert-validated graded relevance benchmarks remain scarce, especially for non-English stat...

User–item interactions in recommender systems are shaped by intertwined factors, such as genuine intent and social conformity. Recent Large Language Model (LLM)-based recommenders leverage textual semantics to improve accuracy and explainability, but often fail to disentangle these factors, limit...