Researchers have developed DuELRec, a novel framework that integrates Large Language Models (LLMs) to improve cross-domain sequential recommendation systems. This approach addresses the issue of negative transfer, where LLMs focusing on text can distort knowledge transfer across different user interaction domains. DuELRec employs a dual-expert system with domain-gated attention and a contrastive learning objective to better capture item-level collaborative signals, outperforming 26 existing methods on real-world datasets. AI
IMPACT Improves recommendation accuracy by better integrating LLMs with collaborative filtering signals.
RANK_REASON Academic paper detailing a new model/framework for a specific AI task. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
