Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation
Nikita Severin, Danil Kartushov, Vladislav Urzhumov, Vladislav Kulikov, Oksana Konovalova + 6 more
TLDR
This paper introduces an efficient knowledge distillation method to integrate LLM-generated user profiles into sequential recommenders without real-time LLM inference.
Key contributions
- Introduces a novel knowledge distillation method for sequential recommenders.
- Leverages LLM-generated textual user profiles to enrich user semantics.
- Eliminates real-time LLM inference costs for enhanced efficiency.
- Requires no architectural modifications or LLM fine-tuning.
Why it matters
LLMs offer deep user understanding for recommenders but are too slow for real-time use. This work provides an efficient way to integrate LLM benefits, making advanced semantic understanding practical for sequential recommendation systems without prohibitive costs.
Original Abstract
Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to enhance user understanding with their reasoning capabilities, yet existing integration approaches create prohibitive inference costs in real time. To address these limitations, we present a novel knowledge distillation method that utilizes textual user profile generated by pre-trained LLMs into sequential recommenders without requiring LLM inference at serving time. The resulting approach maintains the inference efficiency of traditional sequential models while requiring neither architectural modifications nor LLM fine-tuning.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.