# Taxonomy-Guided Zero-Shot Recommendations with LLMs

arXiv: https://arxiv.org/abs/2406.14043 · HTML: https://mlsanity.com/paper/2406.14043/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation](https://mlsanity.com/paper/2305.00447/) (2023)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://mlsanity.com/paper/1803.05170/) (2018)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [Text Is All You Need: Learning Language Representations for Sequential Recommendation](https://mlsanity.com/paper/2305.13731/) (2023)
- [Large Language Models as Zero-Shot Conversational Recommenders](https://mlsanity.com/paper/2308.10053/) (2023)
- [Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited](https://mlsanity.com/paper/2303.13835/) (2023)
- [Towards artificial general intelligence via a multimodal foundation model](https://mlsanity.com/paper/2110.14378/) (2021)
- [Enhancing Recommender Systems with Large Language Model Reasoning Graphs](https://mlsanity.com/paper/2308.10835/) (2023)
- [LM-Critic: Language Models for Unsupervised Grammatical Error Correction](https://mlsanity.com/paper/2109.06822/) (2021)
- [Giraffe: Adventures in Expanding Context Lengths in LLMs](https://mlsanity.com/paper/2308.10882/) (2023)
- [DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation](https://mlsanity.com/paper/2312.11336/) (2023)
- [Aligning Large Language Models with Recommendation Knowledge](https://mlsanity.com/paper/2404.00245/) (2024)
- [Training Large-Scale News Recommenders with Pretrained Language Models in the Loop](https://mlsanity.com/paper/2102.09268/) (2021)
- [Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation](https://mlsanity.com/paper/2306.14462/) (2023)
- [Unified Pretraining for Recommendation via Task Hypergraphs](https://mlsanity.com/paper/2310.13286/) (2023)
- [Confidence-aware Fine-tuning of Sequential Recommendation Systems via Conformal Prediction](https://mlsanity.com/paper/2402.08976/) (2024)

## Built on by (most cited first, 15 of 15)

- [Can Multimodal LLMs Perform Time Series Anomaly Detection?](https://mlsanity.com/paper/2502.17812/) (2025)
- [STAR: A Simple Training-free Approach for Recommendations using Large Language Models](https://mlsanity.com/paper/2410.16458/) (2024)
- [LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation](https://mlsanity.com/paper/2503.01814/) (2025)
- [Large Scale Retrieval for the LinkedIn Feed using Causal Language Models](https://mlsanity.com/paper/2510.14223/) (2025)
- [Entropy-Based Block Pruning for Efficient Large Language Models](https://mlsanity.com/paper/2504.03794/) (2025)
- [Exploring How LLMs Capture and Represent Domain-Specific Knowledge](https://mlsanity.com/paper/2504.16871/) (2025)
- [RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation](https://mlsanity.com/paper/2509.03131/) (2025)
- [Language Models as Semantic Augmenters for Sequential Recommenders](https://mlsanity.com/paper/2510.18046/) (2025)
- [SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2604.09551/) (2026)
- [Social Knowledge for Cross-Domain User Preference Modeling](https://mlsanity.com/paper/2603.10148/) (2026)
- [Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders](https://mlsanity.com/paper/2604.07825/) (2026)
- [From Clicks to Intent: Cross-Platform Session Embeddings with LLM-Distilled Taxonomy for Financial Services Recommendations](https://mlsanity.com/paper/2606.26277/) (2026)
- [Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation](https://mlsanity.com/paper/2608.15949/) (2026)
- [CARA: Cognitive Adaptive Recommendation Agent](https://mlsanity.com/paper/2608.16919/) (2026)
- [RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations](https://mlsanity.com/paper/2608.19735/) (2026)

## Abstract (arXiv)

With the emergence of large language models (LLMs) and their ability to perform a variety of tasks, their application in recommender systems (RecSys) has shown promise. However, we are facing significant challenges when deploying LLMs into RecSys, such as limited prompt length, unstructured item information, and un-constrained generation of recommendations, leading to sub-optimal performance. To address these issues, we propose a novel method using a taxonomy dictionary. This method provides a systematic framework for categorizing and organizing items, improving the clarity and structure of item information. By incorporating the taxonomy dictionary into LLM prompts, we achieve efficient token utilization and controlled feature generation, leading to more accurate and contextually relevant recommendations. Our Taxonomy-guided Recommendation (TaxRec) approach features a two-step process: one-time taxonomy categorization and LLM-based recommendation, enabling zero-shot recommendations without the need for domain-specific fine-tuning. Experimental results demonstrate TaxRec significantly enhances recommendation quality compared to traditional zero-shot approaches, showcasing its efficacy as personal recommender with LLMs. Code is available at https://github.com/yueqingliang1/TaxRec.