TagLLM: A Fine-Grained Tag Generation Approach for Note Recommendation

2026-03-22

AI Summary

Existing tag generation methods in note recommendation systems often suffer from tag redundancy, insufficient user interest guidance, and inadequate fine-grained expression, which collectively limit recommendation performance. To address these limitations, this work proposes TagLLM, a novel approach that leverages a user interest handbook to guide a multimodal chain-of-thought (CoT) mechanism, enabling fine-grained and interpretable tag generation. Furthermore, the authors introduce a tag knowledge distillation strategy to significantly enhance both the generation quality and inference efficiency of smaller models. Online A/B experiments demonstrate that the proposed method substantially improves user experience, yielding a 0.31% increase in average watch time, a 0.96% rise in user interactions, and a remarkable 32.37% boost in page click-through rate under cold-start scenarios.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large Language Models (LLMs) have shown promising potential in E-commerce community recommendation. While LLMs and Multimodal LLMs (MLLMs) are widely used to encode notes into implicit embeddings, leveraging their generative capabilities to represent notes with interpretable tags remains unexplored. In the field of tag generation, traditional close-ended methods heavily rely on the design of tag pools, while existing open-ended methods applied directly to note recommendations face two limitations: (1) MLLMs lack guidance during generation, resulting in redundant tags that fail to capture user interests; (2) The generated tags are often coarse and lack fine-grained representation of notes, interfering with downstream recommendations. To address these limitations, we propose TagLLM, a fine-grained tag generation method for note recommendation. TagLLM captures user interests across note categories through a User Interest Handbook and constructs fine-grained tag data using multimodal CoT Extraction. A Tag Knowledge Distillation method is developed to equip small models with competitive generation capabilities, enhancing inference efficiency. In online A/B test, TagLLM increases average view duration per user by 0.31%, average interactions per user by 0.96%, and page view click-through rate in cold-start scenario by 32.37%, demonstrating its effectiveness.

Problem

• tag generation
• note recommendation
• fine-grained representation
• user interest
• multimodal LLMs

Innovation

• fine-grained tag generation
• User Interest Handbook
• multimodal CoT extraction
• Tag Knowledge Distillation
• note recommendation