Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation

TL;DR

This paper introduces TransRec, a novel recommendation paradigm that enhances large language models' ability to recommend items by using multi-facet identifiers and a specialized grounding method, improving accuracy and validity.

Contribution

TransRec proposes a new multi-facet identifier system and a grounding mechanism to better connect items with language models, addressing limitations of previous ID and description-based methods.

Findings

TransRec outperforms existing methods on three real-world datasets.

Multi-facet identifiers improve item representation and distinctiveness.

The specialized grounding module enhances recommendation accuracy.

Abstract

Harnessing Large Language Models (LLMs) for recommendation is rapidly emerging, which relies on two fundamental steps to bridge the recommendation item space and the language space: 1) item indexing utilizes identifiers to represent items in the language space, and 2) generation grounding associates LLMs' generated token sequences to in-corpus items. However, previous methods exhibit inherent limitations in the two steps. Existing ID-based identifiers (e.g., numeric IDs) and description-based identifiers (e.g., titles) either lose semantics or lack adequate distinctiveness. Moreover, prior generation grounding methods might generate invalid identifiers, thus misaligning with in-corpus items. To address these issues, we propose a novel Transition paradigm for LLM-based Recommender (named TransRec) to bridge items and language. Specifically, TransRec presents multi-facet identifiers, which simultaneously incorporate ID, title, and attribute for item indexing to pursue both distinctiveness and semantics. Additionally, we introduce a specialized data structure for TransRec to ensure generating valid identifiers only and utilize substring indexing to encourage LLMs to generate from any position of identifiers. Lastly, TransRec presents an aggregated grounding module to leverage generated multi-facet identifiers to rank in-corpus items efficiently. We instantiate TransRec on two backbone models, BART-large and LLaMA-7B. Extensive results on three real-world datasets under diverse settings validate the superiority of TransRec.