Feature Extraction for Real Estate Images and Titles with LLMs
Open Access
- 19 June 2026
- journal article
- Published by Sakarya University Journal of Computer and Information Sciences in Sakarya University Journal of Computer and Information Sciences
- No. Advanced O,p. 690-699
Abstract
Images and titles often contain rich latent information about their associated objects, particularly on web-based platforms. Real estate websites provide a clear example, where listing images and titles provide important details that assist users in their decision-making. However, these unstructured elements cannot be directly utilized in downstream machine learning tasks, since their contextual meaning is not directly interpretable. This work aims to transform listing images and titles into structured, tabular representations, making them suitable for analytical and predictive modeling. To this end, we propose a modular framework based on state-of-the-art large language models. The framework incorporates ReAct, LLM-as-a-Judge, and few-shot prompting techniques. Its performance is evaluated on a real-world real estate dataset and compared with BERT and CLIP-based baselines. Experimental results demonstrate that our framework achieves up to a 44.26% improvement in recall for listing attributes, such as the presence of a balcony or the furnishing status of a property.Keywords
Funding Information
- Türkiye Bilimsel ve Teknolojik Araştırma Kurumu (124E135)
This publication has 12 references indexed in Scilit:
- Real Estate Attribute Value Extraction Using Large Language ModelsIEEE Access, 2025
- AutoMV: An Autonomous Agent Framework for Real Estate Marketing Video GenerationProceedings of the AAAI Conference on Artificial Intelligence, 2025
- Structured information extraction from scientific text with large language modelsNature Communications, 2024
- A Prompt Engineering Approach for Structured Data Extraction from Unstructured Text Using Conversational LLMs2023
- Tutorial on PCA and approximate PCA and approximate kernel PCAArtificial Intelligence Review, 2022
- AdaLN: A Vision Transformer for Multidomain Learning and Predisaster Building Information Extraction from ImagesJournal of Computing in Civil Engineering, 2022
- MatSciBERT: A materials domain language model for text mining and information extractionnpj Computational Materials, 2022
- Calibration of Pre-trained Transformers2020
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding2018
- A neural joint model for entity and relation extraction from biomedical textBMC Bioinformatics, 2017