SCoRD: Semantic-Assisted Continual Retriever-Reranker Distillation for LLM-Based Recommendation

Seunghyun Baek, Gyuseok Lee, Seunghan Lee +3

Recommendation systems increasingly adopt a two-stage pipeline, where an ID-based retriever retrieves candidates and an LLM-based reranker refines their rankings. To improve retrie…