Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenization

TL;DR

This paper introduces a two-stage framework that aligns traditional recommendation signals with large language models through semantic tokenization and supervised alignment tasks, significantly enhancing recommendation accuracy and scalability.

Contribution

It presents a novel semantic alignment method combining item tokenization and supervised learning to bridge collaborative signals with LLM semantics in recommendation systems.

Findings

Improved recall metrics in experiments

Enhanced scalability of recommendation systems

Reduced inference latency through pre-caching

Abstract

Large language models (LLMs), endowed with exceptional reasoning capabilities, are adept at discerning profound user interests from historical behaviors, thereby presenting a promising avenue for the advancement of recommendation systems. However, a notable discrepancy persists between the sparse collaborative semantics typically found in recommendation systems and the dense token representations within LLMs. In our study, we propose a novel framework that harmoniously merges traditional recommendation models with the prowess of LLMs. We initiate this integration by transforming ItemIDs into sequences that align semantically with the LLMs space, through the proposed Alignment Tokenization module. Additionally, we design a series of specialized supervised learning tasks aimed at aligning collaborative signals with the subtleties of natural language semantics. To ensure practical applicability, we optimize online inference by pre-caching the top-K results for each user, reducing latency and improving effciency. Extensive experimental evidence indicates that our model markedly improves recall metrics and displays remarkable scalability of recommendation systems.