# TagGPT: Large Language Models are Zero-shot Multimodal Taggers

arXiv: https://arxiv.org/abs/2304.03022 · HTML: https://mlsanity.com/paper/2304.03022/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2023.

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

- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [LLM-Rec: Personalized Recommendation via Prompting Large Language Models](https://mlsanity.com/paper/2307.15780/) (2023)
- [ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation](https://mlsanity.com/paper/2308.11131/) (2023)
- [Vision-Language Instruction Tuning: A Review and Analysis](https://mlsanity.com/paper/2311.08172/) (2023)
- [Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation](https://mlsanity.com/paper/2408.03533/) (2024)
- [LLMs for User Interest Exploration in Large-scale Recommendation Systems](https://mlsanity.com/paper/2405.16363/) (2024)
- [A Survey on Large Language Models in Multimodal Recommender Systems](https://mlsanity.com/paper/2505.09777/) (2025)
- [X-Reflect: Cross-Reflection Prompting for Multimodal Recommendation](https://mlsanity.com/paper/2408.15172/) (2024)
- [Large Language Models Make Sample-Efficient Recommender Systems](https://mlsanity.com/paper/2406.02368/) (2024)
- [Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Models](https://mlsanity.com/paper/2408.16296/) (2024)
- [Who You Are Matters: Bridging Topics and Social Roles via LLM-Enhanced Logical Recommendation](https://mlsanity.com/paper/2505.10940/) (2025)
- [Serendipitous Recommendation with Multimodal LLM](https://mlsanity.com/paper/2506.08283/) (2025)
- [Full-Stack Optimized Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation](https://mlsanity.com/paper/2501.13344/) (2025)
- [SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systems](https://mlsanity.com/paper/2512.12938/) (2025)
- [MERIT: Mitigating Exposure Bias in Generative XMC for User-Interest Propensity Modeling](https://mlsanity.com/paper/2608.28931/) (2026)

## Abstract (arXiv)

Tags are pivotal in facilitating the effective distribution of multimedia content in various applications in the contemporary Internet era, such as search engines and recommendation systems. Recently, large language models (LLMs) have demonstrated impressive capabilities across a wide range of tasks. In this work, we propose TagGPT, a fully automated system capable of tag extraction and multimodal tagging in a completely zero-shot fashion. Our core insight is that, through elaborate prompt engineering, LLMs are able to extract and reason about proper tags given textual clues of multimodal data, e.g., OCR, ASR, title, etc. Specifically, to automatically build a high-quality tag set that reflects user intent and interests for a specific application, TagGPT predicts large-scale candidate tags from a series of raw data via prompting LLMs, filtered with frequency and semantics. Given a new entity that needs tagging for distribution, TagGPT introduces two alternative options for zero-shot tagging, i.e., a generative method with late semantic matching with the tag set, and another selective method with early matching in prompts. It is well noticed that TagGPT provides a system-level solution based on a modular framework equipped with a pre-trained LLM (GPT-3.5 used here) and a sentence embedding model (SimCSE used here), which can be seamlessly replaced with any more advanced one you want. TagGPT is applicable for various modalities of data in modern social media and showcases strong generalization ability to a wide range of applications. We evaluate TagGPT on publicly available datasets, i.e., Kuaishou and Food.com, and demonstrate the effectiveness of TagGPT compared to existing hashtags and off-the-shelf taggers. Project page: https://github.com/TencentARC/TagGPT.