Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders

TL;DR

This paper systematically compares pure and augmented large language model recommenders, providing a taxonomy, a unified evaluation platform, and insights into their relative effectiveness and future research directions.

Contribution

It introduces a novel taxonomy classifying LLM recommenders, and develops a unified benchmarking platform for fair comparison of different approaches.

Findings

Unified evaluation platform for LLM recommenders

Taxonomy distinguishing pure and augmented approaches

Insights into design choices affecting performance

Abstract

Large language models (LLMs) have introduced new paradigms for recommender systems by enabling richer semantic understanding and incorporating implicit world knowledge. In this study, we propose a systematic taxonomy that classifies existing approaches into two categories: (1) Pure LLM Recommenders, which rely solely on LLMs, and (2) Augmented LLM Recommenders, which integrate additional non-LLM techniques to enhance performance. This taxonomy provides a novel lens through which to examine the evolving landscape of LLM-based recommendation. To support fair comparison, we introduce a unified evaluation platform that benchmarks representative models under consistent experimental settings, highlighting key design choices that impact effectiveness. We conclude by discussing open challenges and outlining promising directions for future research. This work offers both a comprehensive overview and practical guidance for advancing next-generation LLM-powered recommender.