Language Models as Semantic Augmenters for Sequential Recommenders

TL;DR

This paper presents LaMAR, a framework that uses Large Language Models to automatically generate semantic context signals, enriching sequential user data and improving recommendation performance.

Contribution

Introduces LaMAR, a novel LLM-driven method for semantic enrichment of sequential data, enhancing recommender systems with high-diversity contextual signals.

Findings

Consistent performance improvements on benchmark tasks

Generated signals exhibit high semantic diversity

Enhances the representational capacity of downstream models

Abstract

Large Language Models (LLMs) excel at capturing latent semantics and contextual relationships across diverse modalities. However, in modeling user behavior from sequential interaction data, performance often suffers when such semantic context is limited or absent. We introduce LaMAR, a LLM-driven semantic enrichment framework designed to enrich such sequences automatically. LaMAR leverages LLMs in a few-shot setting to generate auxiliary contextual signals by inferring latent semantic aspects of a user's intent and item relationships from existing metadata. These generated signals, such as inferred usage scenarios, item intents, or thematic summaries, augment the original sequences with greater contextual depth. We demonstrate the utility of this generated resource by integrating it into benchmark sequential modeling tasks, where it consistently improves performance. Further analysis shows that LLM-generated signals exhibit high semantic novelty and diversity, enhancing the representational capacity of the downstream models. This work represents a new data-centric paradigm where LLMs serve as intelligent context generators, contributing a new method for the semi-automatic creation of training data and language resources.