analiza aiqbench
This paper applies LLMs to a practical data-infrastructure problem: generating searchable keywords for virtual datasets in a data virtualization service. It compares five text-selection strategies across three LLM generators and two embedding methods, and finds that performance depends mainly on the quality of the source text descriptions. For AI readers, the main takeaway is that LLM keyword generation is only as good as the metadata it receives, and the results are from a single research group's case studies, so they should be tested before being assumed to generalize.
Automated Keyword Generation Using LLMs in a High-Volume Data Virtualization Service
arXiv:2610.41893v1 Announce Type: new Abstract: In modern data infrastructure, a data virtualization service (DVS) allows users to create many versions of source datasets for different processing tasks. For example, a multivariate or multi-modality dataset can be used for different machine learning tasks (e.g., classification, detection, segmentation, forecasting, and so on). Data selection, participation, integration, and preprocessing in different tasks result in many virtual datasets [Khan et al., SSC 2026]. Meanwhile, different users need to discover existing virtual datasets frequently and easily to avoid duplicate efforts. To enable an effective search engine in a DVS, it is desirable to automatically generate keywords for each virtual dataset. In this work, we present a solution for generating keywords for virtual datasets using large language models (LLMs). We propose five strategies for selecting different collections of text data for processing by the LLMs. We applied the five strategies to virtual datasets created in five application case studies with different source datasets. We conducted experiments with three LLM generators and two embedding techniques. The experiments show that the performances of the five strategies depend on the quality of the text descriptions. The results help us adopt a multi-strategy implementation of a new keyword generation service (KGS) as part of an extended DVS. The work demonstrates that the capability of automated keyword generation is indispensable for a high-volume DVS that is dataset-rich and frequently accessed.
Abstract:In modern data infrastructure, a data virtualization service (DVS) allows users to create many versions of source datasets for different processing tasks. For example, a multivariate or multi-modality dataset can be used for different machine learning tasks (e.g., classification, detection, segmentation, forecasting, and so on). Data selection, participation, integration, and preprocessing in different tasks result in many virtual datasets [Khan et al., SSC 2026]. Meanwhile, different users need to discover existing virtual datasets frequently and easily to avoid duplicate efforts. To enable an effective search engine in a DVS, it is desirable to automatically generate keywords for each virtual dataset. In this work, we present a solution for generating keywords for virtual datasets using large language models (LLMs). We propose five strategies for selecting different collections of text data for processing by the LLMs. We applied the five strategies to virtual datasets created in five application case studies with different source datasets. We conducted experiments with three LLM generators and two embedding techniques. The experiments show that the performances of the five strategies depend on the quality of the text descriptions. The results help us adopt a multi-strategy implementation of a new keyword generation service (KGS) as part of an extended DVS. The work demonstrates that the capability of automated keyword generation is indispensable for a high-volume DVS that is dataset-rich and frequently accessed.
Artificial Intelligence (cs.AI)
arXiv:2610.41893 [cs.AI]
(or arXiv:2610.41893v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.41893 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 318 cuvinte
Subiecte conexe
Advancing Ligand-based Virtual Screening and Molecular Generation with Pretrained Molecular Embedding Distance
arXiv · 9 iun. 2026
Robo-Saber: Generating and Simulating Virtual Reality Players
arXiv · 30 sept. 2026
From Prompt to Service: An SLM-Based Agent Orchestration Gateway for AI-Driven Virtual Worlds
arXiv · 3 iun. 2026
Coverage-Aware Virtual IMU Augmentation for Low-Resource Human Activity Recognition
arXiv · 16 sept. 2026