New framework ExpArt-KG enhances LVLMs for artwork description

Researchers have developed ExpArt-KG, a framework designed to enhance the descriptive capabilities of Large Vision-Language Models (LVLMs) for artwork. This method integrates knowledge graphs with retrieval-augmented generation, allowing LVLMs to more comprehensively and accurately detail factual relationships within an image. The system iteratively generates descriptions and retrieves relevant information from a knowledge graph, using a correctness judgment to efficiently acquire necessary facts. Experiments show this approach improves the detail of artwork explanations and reduces knowledge retrieval costs while maintaining generation quality. AI

IMPACT This framework could lead to more detailed and accurate AI-generated descriptions of visual content, particularly in specialized domains like art.

RANK_REASON The cluster contains an academic paper detailing a new framework and methodology for AI model enhancement. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• alphaXiv
• arXiv
• DagsHub
• ExpArt-KG
• Hugging Face
• knowledge graph
• Large Vision Language Models
• retrieval-augmented generation

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →