Distilling LLM Reasoning into Dense Encoders: Bridging the Accuracy-Efficiency Gap in Recommendation

Large Language Models (LLMs) have shown remarkable potential in recommendation systems but suffer from prohibitive inference latency.Existing distillation approaches typically target Small Language Models (SLMs) or Conventional Recommendation Models (CRMs), yet face a critical trade-off between computational cost and semantic reasoning capacity.To bridge this accuracy-efficiency gap, we introduce Reasoning-to-Encoder Distillation (R2END), a framework that establishes a text encoder as the optimal student architecture for scalable recommendation.Unlike methods that mimic token generation, R2END compresses the teacher's reasoning into a dense vector space via a semantic alignment objective, effectively capturing user-item dynamics.Extensive experiments on four datasets demonstrate that R2END not only outperforms stateof-the-art baselines but also achieves drastically reduced latency, offering a sweet spot for recommendation. LLM-to-SLMR2SLM SLIM RDRec LLM-to-CRM RLMRec R2SASRec DLLM2Rec Accuracy (NDCG@5) Latency (ms) LLM-to-SLM Accurate, but Slow & Costly LLM-to-CRM Fast, but Lack of Reasoning R2END (Ours) Accurate & Fast