LLM-Powered Framework to Explore Summarized Aggregated Multimedia Vertical Web Search Results

Muhammad Wajeeh Uz Zaman; Umer Rashid; Abur Rehman Khan

Authors

Muhammad Wajeeh Uz Zaman Department of Computer Sciences, Quaid-i-Azam University Islamabad, Pakistan
Umer Rashid Department of Computer Sciences, Quaid-i-Azam University Islamabad, Pakistan
Abur Rehman Khan School of Computer Science, Centre for Data Science, Queensland University of Technology, Brisbane, Australia

Keywords:

Aggregated Search, LLMs, Multimedia, Vertical Search, Exploratory Search

Abstract

The exponential growth of multimedia content has shifted users’ information-seeking behavior from lookup-based to exploratory search. To aid exploration, search engines adopted two prominent approaches: presenting results in verticals (web images, videos, news) and integrating Generative AI (GenAI) to enable rapid comprehension. However, integrations like GenAI primarily focus on lookup search by providing basic text summaries of top results, which also hinder users’ ability to explore information through multimedia. Consequently, users make additional navigation efforts (clicking, scrolling, switching verticals), hindering information exploration. In this approach, we propose a framework that summarizes vertical search results into comprehensive documents. The framework is powered by a large language model (LLM) that extracts topics from search results and groups semantically similar multimedia results across verticals into unified topic-based summaries. This unified interaction reduces users' navigation effort and increases interest in exploration. We evaluated our approach using ROUGE across three domains (Movies, Music, and Sports) and conducted a system usability study with 31 participants, using the Bing search engine as a baseline. The proposed system achieved an average ROUGE F1 at: R-1 = 0.67 ± 0.15, R-2 = 0.26 ± 0.17, R-L = 0.60 ± 0.20. The navigation efforts were significantly reduced in terms of clicks (21.5 vs. 30.8, p < 0.01), scrolls (74.6 vs. 218.4, p < 0.001), and vertical switches (0 vs. 3.7). The average system usability score was reported at 88%, significantly higher than baseline (77%, p < 0.05). These results confirm that our framework reduces exploratory navigation efforts while maintaining high user satisfaction.

References

Muhammad Wajeeh Uz Zaman, Umer Rashid, “ExSMuV: [Ex]ploration software for [S]ummarized [Mu]ltimedia [V]ertical search results,” SoftwareX, vol. 33, 2026, doi: 10.1016/j.softx.2025.102501.

U. Rashid and A. R. Khan, “Discovery work-space design to explore semantically aggregated graph-cluster spaces of multimedia document results,” Behav. Inf. Technol., Mar. 2025, doi: 10.1080/0144929X.2025.2532151.

Leila Shahrzadi, Ali Mansouri, “Causes, consequences, and strategies to deal with information overload: A scoping review,” Int. J. Inf. Manag. Data Insights, vol. 4, no. 2, p. 100261, 2024, doi: https://doi.org/10.1016/j.jjimei.2024.100261.

Holli Anne Passmore, Ashley N. Krause, “The beyond-human natural world: Providing meaning and making meaning,” Int. J. Environ. Res. Public Health, vol. 20, no. 12, p. 6170, 2023, [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/37372757/

Timothée Schmude, Laura Koesten, “Information that matters: Exploring information needs of people affected by algorithmic decisions,” Int. J. Hum. Comput. Stud., vol. 193, p. 103380, 2025, doi: https://doi.org/10.1016/j.ijhcs.2024.103380.

M. W. U. Zaman, A. R. Khan, and U. Rashid, “Towards Summarization of Aggregated Multimedia Verticals Web Search Results,” 18th IEEE Int. Conf. Emerg. Technol. ICET 2023, pp. 263–268, 2023, doi: 10.1109/ICET59753.2023.10374811.

S. Naseer, U. Rashid, M. Saddal, and A. R. Khan, “SERB: an interactive exploration mechanism for blind web users to explore web search content,” Univers. Access Inf. Soc. 2025 243, vol. 24, no. 3, pp. 2335–2350, Feb. 2025, doi: 10.1007/s10209-025-01199-2.

E. Amer and T. Elboghdadly, “The End of the Search Engine Era and the Rise of Generative AI: A Paradigm Shift in Information Retrieval,” 4th Int. Mobile, Intelligent, Ubiquitous Comput. Conf. MIUCC 2024, pp. 374–379, 2024, doi: 10.1109/MIUCC62295.2024.10783559.

A. R. Ashraf, T. K. Mackey, and A. Fittler, “Search Engines and Generative Artificial Intelligence Integration: Public Health Risks and Recommendations to Safeguard Consumers Online,” JMIR Public Heal. Surveill., vol. 10, no. 1, p. e53086, Mar. 2024, doi: 10.2196/53086.

Pubali Mukherjee, Varsha Jain, “How lack of choice to opt-out of generative artificial intelligence in traditional search engines drives consumer switching intentions: The mechanism of empowerment,” J. Retail. Consum. Serv., vol. 88, p. 104506, 2026, doi: https://doi.org/10.1016/j.jretconser.2025.104506.

Tajmir Khan, Umer Rashid, “End-to-end vertical web search pseudo relevance feedback queries recommendation software,” SoftwareX, vol. 27, p. 101872, 2024, doi: https://doi.org/10.1016/j.softx.2024.101872.

Y. Liu, C. Qin, X. Ma, J. Chen, H. He, and J. Mao, “Characterising exploratory search tasks: Evidence from different fields,” J. Inf. Sci., 2025, doi: 10.1177/01655515251330611.

Milad Momeni, Orland Hoeber, “A study of search result aggregation approaches for the digital humanities,” J. Assoc. Inf. Sci. Technol., 2025, doi: https://doi.org/10.1002/asi.70006.

Soyoung Kim, Randi Priluck, “Consumer Responses to Generative AI Chatbots Versus Search Engines for Product Evaluation,” J. Theor. Appl. Electron. Commer. Res, vol. 20, no. 2, p. 93, 2025, doi: https://doi.org/10.3390/jtaer20020093.

Lin Liu, Jiajun Meng, “LLM technologies and information search,” J. Econ. Technol., vol. 2, no. 4, pp. 269–277, 2024, doi: 10.1016/j.ject.2024.08.007.

Nakyung Kim, Yong Gu Ji, “Exploratory Search with Generative AI: An Empirical Study on the Impact of Interaction Design Strategies on Information Exploration and Cognitive Load,” Int. J. Hum. Comput. Stud., vol. 210, p. 103771, 2026, doi: https://doi.org/10.1016/j.ijhcs.2026.103771.

A. Akintoye, “Installing Laravel, Development, and Test Tools Installation,” API Dev. with Laravel, pp. 21–64, 2025, doi: 10.1007/979-8-8688-1576-8_2.

Göker Cebeci, Banu Diri, “Disentangling Technical and Content Attributes in Search Engine Ranking: A Comparative Study of Google and Bing,” IEEE Access, 2026, doi: 10.1109/ACCESS.2026.3657977.

Boni García, Filippo Ricca, “Test automation with selenium: A survey,” Inf. Softw. Technol., vol. 194, p. 108077, 2026, doi: https://doi.org/10.1016/j.infsof.2026.108077.

Shariq Murtuza, “Forensic Implications of Localized AI: Artifact Analysis of Ollama, LM Studio, and llama,” arXiv:2603.23996, 2026, [Online]. Available: https://arxiv.org/abs/2603.23996

Alexander Amini, Anna Banaszak, Harold Benoit, “LFM2 Technical Report,” arXiv:2511.23404, 2025, [Online]. Available: https://arxiv.org/abs/2511.23404

“WhatPulse 5.0: Mouse Scrolls, Distance, oh my! | WhatPulse Blog.” Accessed: Apr. 21, 2026. [Online]. Available: https://whatpulse.org/blog/whatpulse-5-0-mouse-scrolls-distance-oh-my-ded09dc3e64d

“AutoHotkey.” Accessed: Mar. 11, 2026. [Online]. Available: https://www.autohotkey.com/

Mousumi Akter, Naman Bansal, “Assessing the effectiveness of ROUGE as unbiased metric in Extractive vs. Abstractive summarization techniques,” J. Comput. Sci., vol. 87, p. 102571, 2025, doi: https://doi.org/10.1016/j.jocs.2025.102571.

Haopeng Zhang, Philip S. Yu, “A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models Haopeng Zhang, Philip S. Yu, Jiawei Zhang,” ACM Comput. Surv., 2024, [Online]. Available: https://arxiv.org/abs/2406.11289

“Can Generative AI Replace Search Engines for Learning? Understanding Student Preferences, Use and Perceived Proficiency in Using AI | TechTrends | Springer Nature Link.” Accessed: Apr. 21, 2026. [Online]. Available: https://link.springer.com/article/10.1007/s11528-025-01095-9

A. M. Garcia-Carmona, M. L. Prieto, E. Puertas, and J. J. Beunza, “Leveraging Large Language Models for Accurate Retrieval of Patient Information From Medical Reports: Systematic Evaluation Study,” JMIR AI, vol. 4, 2025, doi: 10.2196/68776.

Panagiota Papastamoulou, Nikos Antonopoulos, “Artificial Intelligence in E-Commerce: A Comparative Analysis of Best Practices Across Leading Platforms,” Systems, vol. 13, no. 9, p. 746, 2025, doi: https://doi.org/10.3390/systems13090746.

Joon Soo Lim, Nalae Hong, “Perceived search overload, generative AI credibility, and comparative usefulness: a channel complementarity approach to health information seeking,” Heal. New Media Res., vol. 9, no. 1, pp. 124–145, 2025, doi: https://doi.org/10.22720/hnmr.2025.00115.

Gusman Lesmana, Indra Prasetia, “Depth Counseling for Students Experiencing Cognitive Crisis in Learning,” J. Educ. Stud. Multidiscip. Approaches, vol. 6, no. 1, 2026, doi: 10.51383/jesma.2026.142.