Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers

TL;DR

This paper introduces a novel framework called GRLM that uses semantically rich Term IDs for improved, robust, and scalable generative recommendation systems leveraging Large Language Models.

Contribution

The paper proposes TIDs as standardized item identifiers and introduces GRLM, a framework that employs context-aware generation and instruction fine-tuning for enhanced recommendation performance.

Findings

GRLM outperforms baseline methods on real-world datasets.

TIDs effectively bridge semantic gaps and improve recommendation accuracy.

The approach demonstrates robustness and scalability in various scenarios.

Abstract

Leveraging the vast open-world knowledge and understanding capabilities of Large Language Models (LLMs) to develop general-purpose, semantically-aware recommender systems has emerged as a pivotal research direction in generative recommendation. However, existing methods face bottlenecks in constructing item identifiers. Text-based methods introduce LLMs' vast output space, leading to hallucination, while methods based on Semantic IDs (SIDs) encounter a semantic gap between SIDs and LLMs' native vocabulary, requiring costly vocabulary expansion and alignment training. To address this, this paper introduces Term IDs (TIDs), defined as a set of semantically rich and standardized textual keywords, to serve as robust item identifiers. We propose GRLM, a novel framework centered on TIDs, employs Context-aware Term Generation to convert item's metadata into standardized TIDs and utilizes Integrative Instruction Fine-tuning to collaboratively optimize term internalization and sequential recommendation. Additionally, Elastic Identifier Grounding is designed for robust item mapping. Extensive experiments on real-world datasets demonstrate that GRLM significantly outperforms baselines across multiple scenarios, pointing a promising direction for generalizable and high-performance generative recommendation systems.