LaPR: Latent Preference Reasoning for Generative Personalized Retrieval
Compresses teacher-written retrieval steps into learned discrete slot codes. Predicts how many slots a query and user history need, then generates the slots and an item identifier without writing a natural-language rationale.
First public: · Added to this list: November 9, 2026
Author-hosted preprint upload date. Date source.
Cite this paper
Published version
LaPR: Latent Preference Reasoning for Generative Personalized Retrieval
Hanze Guo, Shunyu Zhang, Jiakai Tang, Jingwei Zhuo, Yi Zhang, Xuanping Li, Xiao Zhou
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026, pp. 51279-51297.
Explore this approach
Thinking tokens — Give a model extra tokens for computation, such as pauses, filler symbols, or learned planning tokens. These tokens need not spell out the solution.
Internalized reasoning — Learn from worked solutions so that some or all of the reasoning can later happen without writing those steps. Training may use a separate teacher model or progressively remove written steps from the model being trained.