Preprint
Jul 2026
LaRec: Unleashing LLM-based Latent Reasoning for Generative Recommendation
This work proposes LaRec, an efficient generative recommendation framework designed to unleash the potential of latent reasoning in LLMs by designing Latent Pre-training that empowers LLMs with latent reasoning capabilities by providing rich supervisory signals to the latent space reasoning via step-level alignment and process direction alignment.
Yu Xia, Zihan Lin, Wei Yang et al.
· 0 citations