QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling

TL;DR

QARM V2 introduces a unified framework that integrates large language model semantic understanding with recommendation system requirements to improve user sequence modeling, addressing limitations of traditional ID-based methods.

Contribution

The paper presents QARM V2, a novel approach that effectively combines LLM semantic representations with RecSys, overcoming representation mismatch and unlearning issues.

Findings

Enhanced user sequence modeling accuracy.

Better generalization in recommendation tasks.

Bridging semantic understanding with business needs.

Abstract

With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys). Traditional RecSys relies on ID-based embeddings for user sequence modeling in the General Search Unit (GSU) and Exact Search Unit (ESU) paradigm, which suffers from low information density, knowledge isolation, and weak generalization ability. While LLMs offer complementary strengths with dense semantic representations and strong generalization, directly applying LLM embeddings to RecSys faces critical challenges: representation unmatch with business objectives and representation unlearning end-to-end with downstream tasks. In this paper, we present QARM V2, a unified framework that bridges LLM semantic understanding with RecSys business requirements for user sequence modeling.