SavedAdd your journal

Journals / Sakarya University Journal of Computer and Information Sciences / 2026 / Volume: 9 Issue: 3

Feature Extraction for Real Estate Images and Titles with LLMs

Afra Arslan(ILab)0009-0006-4857-5155
Tan Doruk Yetki(ILab)0009-0000-7304-2605
Arda Yücel(ILab)0009-0003-2926-9257
Hacer Turgut(ILab)0000-0002-7680-0878
Ömür Bali(ILab)0009-0005-4907-649X
Gülfem Işıklar Alptekin(GALATASARAY UNIVERSITY, FACULTY OF ENGINEERING AND TECHNOLOGY, DEPARTMENT OF COMPUTER ENGINEERING)0000-0003-0146-1581
Günce Keziban Orman(GALATASARAY UNIVERSITY, FACULTY OF ENGINEERING AND TECHNOLOGY, DEPARTMENT OF COMPUTER ENGINEERING)0000-0003-0402-8417
Pages
—
Publication Date
2026-06-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

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.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Images and titles often contain rich latent information about their associated objects, particularly on web-based platforms.
📊
Key Findings & Data:The framework incorporates ReAct, LLM-as-a-Judge, and few-shot prompting techniques.
💡
Conclusion & Impact: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.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:CLIP · Feature extraction · Information retrieval

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.

🔖

Cite This Article

Arslan, A., Yetki, T. D., Yücel, A., Turgut, H., Bali, Ö., Alptekin, G. I., Orman, G. K. (2026). Feature Extraction for Real Estate Images and Titles with LLMs. Sakarya University Journal of Computer and Information Sciences, Volume: 9 Issue: 3. https://doi.org/10.35377/saucis...1829206

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (21)

  1. T. Brown et al., Language models are few-shot learners, Adv. Neural Inf. Process. Syst., 33 (2020), 1877–1901.
  2. J. Dagdelen et al., Structured information extraction from scientific text with large language models, Nat. Commun., 15(1) (2024), 1418.
  3. S. Desai and G. Durrett, Calibration of pre-trained transformers, in Proc. 2020 Conf. Empirical Methods Nat. Lang. Process. (EMNLP), Association for Computational Linguistics, (2020), 295–302.
  4. F. Feng, Y. Yang, D. Cer, N. Arivazhagan, and W. Wang, Language-agnostic BERT sentence embedding, arXiv preprint arXiv:2007.01852, 2020. https://arxiv.org/abs/2007.01852
  5. Y. Guo, C. Wang, S. X. Yu, F. McKenna, and K. H. Law, AdaLN: a vision transformer for multidomain learning and predisaster building information extraction from images, J. Comput. Civ. Eng., 36(5) (2022), 04022024.
  6. T. Gupta, M. Zaki, N. M. A. Krishnan, and Mausam, MatSciBERT: a materials domain language model for text mining and information extraction, Comput. Mater. Sci., 8(1) (2022), 102.
  7. K. Han, Y. Wang, J. Guo, Y. Tang, and E. Wu, Vision GNN: an image is worth graph of nodes, Adv. Neural Inf. Process. Syst., 35 (2022), 8291–8303.
  8. ilab-core, LLM-based real estate information extraction, GitHub repository. https://github.com/ilab-core/llm-based-real-estate-information-extraction
  9. M. Kvet, M. Potocˇa´r, and S. Tatarka, Real estate attribute value extraction using large language models, IEEE Access, 13 (2025).
  10. F. Li, M. Zhang, G. Fu, and D. Ji, A neural joint model for entity and relation extraction from biomedical text, BMC Bioinformatics, 18 (2017), 1–11.
  11. W.-C. Liao, D. Y. Koh, G. Yin, and S. Zheng, Feng Shui meets AI: Measuring its economic value in commercial real estate, MIT Center for Real Estate Research Paper No. 25/08, Nov. 2025.
  12. S. Marukatat, Tutorial on PCA and approximate PCA and approximate kernel PCA, Artif. Intell. Rev., 56(6) (2023), 5445–5477.
  13. OpenAI, OpenAI, online resource. https://openai.com
  14. A. Radford et al., Learning transferable visual models from natural language supervision, arXiv preprint arXiv:2103.00020, 2021. https://arxiv.org/abs/2103.00020
  15. G. Salton, Automatic Information Organization and Retrieval, McGraw-Hill Book Company, New York, 1968.
  16. K. Spa¨rck Jones, A theoretical comparison of recall and precision, J. Doc., 28(1) (1972), 11–21.
  17. A. Vijayan, A prompt engineering approach for structured data extraction from unstructured text using conversational LLMs, in Proc. 2023 6th Int. Conf. Algorithms, Comput. Artif. Intell. (ACAI ’23), Association for Computing Machinery, (2024), 183–189.
  18. A. Wang, A. Singh, J. Michael, F. Hill, O. Levy, and S. R. Bowman, GLUE: a multi-task benchmark and analysis platform for natural language understanding, in Proc. 7th Int. Conf. Learn. Represent. (ICLR), 2019.
  19. K. Wu, S. Yuan, C. Shen, L. Xu, and M. Chen, AutoMV: An autonomous agent framework for real estate marketing video generation, Proc. AAAI Conf. Artif. Intell., 39(28) (2025), 29715–29717.
  20. S. Yao et al., ReAct: Synergizing reasoning and acting in language models, arXiv preprint arXiv:2210.03629, 2023. https://arxiv.org/abs/2210.03629
  21. L. Zheng et al., Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena, arXiv preprint arXiv:2306.05685, 2023. https://arxiv.org/abs/2306.05685