一作SIGIR 2026Oral· Information Retrieval (Full)
Factorized Latent Reasoning for LLM-based Recommendation
Tianqi Gao · Chengkai Huang · Zihan Wang · Cao Liu · Ke Zeng · Lina Yao
摘要
Large language models (LLMs) have recently been adopted for recommendation by framing user preference modeling as a language generation problem. However, existing latent reasoning approaches typically represent user intent with a single latent vector, which struggles to capture the inherently mul...