Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 52 of its 77 references that are in the map. First posted on arXiv 29 May 2025.
Builds on
52 of 77 references.
References · 52
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
- 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
- 2018Self-Attentive Sequential Recommendationcited by 1,184
- 2017Neural Collaborative Filteringcited by 1,111
- 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
- 2022Autoregressive Image Generation using Residual Quantizationcited by 722
38 more
- 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
- 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
- 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 402
- 2023A Survey on Large Language Models for Recommendationcited by 379
- 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 337
- 2020S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximizationcited by 311
- 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 309
- 2024Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoderscited by 224
- 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 179
- 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
- 2023Text Is All You Need: Learning Language Representations for Sequential Recommendationcited by 149
- 2023Large Language Models as Zero-Shot Conversational Recommenderscited by 127
- 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 116
- 2024Learnable Item Tokenization for Generative Recommendationcited by 110
- 2024Data-efficient Fine-tuning for LLM-based Recommendationcited by 104
- 2023How to Index Item IDs for Recommendation Foundation Modelscited by 102
- 2023Leveraging Large Language Models for Sequential Recommendationcited by 78
- 2023A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systemscited by 73
- 2023GenRec: Large Language Model for Generative Recommendationcited by 63
- 2024MACRec: a Multi-Agent Collaboration Framework for Recommendationcited by 58
- 2023LlamaRec: Two-Stage Recommendation using Large Language Models for Rankingcited by 53
- 2024Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender Systemcited by 50
- 2024Harnessing Large Language Models for Text-Rich Sequential Recommendationcited by 38
- 2023Linear Recurrent Units for Sequential Recommendationcited by 32
- 2024Customizing Language Models with Instance-wise LoRA for Sequential Recommendationcited by 32
- 2023Large Language Models for Intent-Driven Session Recommendationscited by 30
- 2023Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendationcited by 29
- 2024Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregationcited by 26
- 2024Large Language Models are Learnable Planners for Long-Term Recommendationcited by 24
- 2024CALRec: Contrastive Alignment of Generative LLMs for Sequential Recommendationcited by 24
- 2024RDRec: Rationale Distillation for LLM-based Recommendationcited by 22
- 2024CFaiRLLM: Consumer Fairness Evaluation in Large-Language Model Recommender Systemcited by 18
- 2024Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Trackingcited by 18
- 2024Unifying Generative and Dense Retrieval for Sequential Recommendationcited by 18
- 2023One Model for All: Large Language Models are Domain-Agnostic Recommendation Systemscited by 17
- 2025Collaborative Retrieval for Large Language Model-based Conversational Recommender Systemscited by 16
- 2023Large Language Models are Not Stable Recommender Systemscited by 13
- 2021Mitigating the Position Bias of Transformer Models in Passage Re-Rankingcited by 10
50 most cited of 52 All 52 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.