A Survey on Open Dataset Search in the LLM Era: Retrospectives and Perspectives

2025-08-31

AI Summary

With the rise of large language models (LLMs), there is an urgent need for efficient and precise retrieval from open datasets. Existing approaches—relying primarily on metadata and keyword matching—are inadequate for semantic, context-aware, and interactive data discovery. Method: This paper systematically redefines the dataset search paradigm by proposing a tripartite technical framework: (1) example-driven query formulation, (2) content-level semantic matching, and (3) retrieval acceleration. It introduces the first bidirectional co-enhancement framework linking dataset search and LLMs: LLMs improve query understanding, interactive guidance, and semantic relevance scoring; conversely, search results empower retrieval-augmented generation (RAG) and high-quality dataset curation. Contribution/Results: We establish the first comprehensive taxonomy covering the full dataset lifecycle, distill core technical challenges, and identify key open problems. This work lays a theoretical foundation and provides practical guidelines for advancing data intelligence and fostering synergistic evolution between data and models.

Technology Category

• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

High-quality datasets are typically required for accomplishing data-driven tasks, such as training medical diagnosis models, predicting real-time traffic conditions, or conducting experiments to validate research hypotheses. Consequently, open dataset search, which aims to ensure the efficient and accurate fulfillment of users' dataset requirements, has emerged as a critical research challenge and has attracted widespread interest. Recent studies have made notable progress in enhancing the flexibility and intelligence of open dataset search, and large language models (LLMs) have demonstrated strong potential in addressing long-standing challenges in this area. Therefore, a systematic and comprehensive review of the open dataset search problem is essential, detailing the current state of research and exploring future directions. In this survey, we focus on recent advances in open dataset search beyond traditional approaches that rely on metadata and keywords. From the perspective of dataset modalities, we place particular emphasis on example-based dataset search, advanced similarity measurement techniques based on dataset content, and efficient search acceleration techniques. In addition, we emphasize the mutually beneficial relationship between LLMs and open dataset search. On the one hand, LLMs help address complex challenges in query understanding, semantic modeling, and interactive guidance within open dataset search. In turn, advances in dataset search can support LLMs by enabling more effective integration into retrieval-augmented generation (RAG) frameworks and data selection processes, thereby enhancing downstream task performance. Finally, we summarize open research problems and outline promising directions for future work. This work aims to offer a structured reference for researchers and practitioners in the field of open dataset search.

Problem

• Surveying open dataset search advancements beyond traditional metadata methods
• Exploring LLMs' role in enhancing query understanding and semantic modeling
• Addressing efficient search acceleration and content-based similarity techniques

Innovation

• Example-based dataset search techniques
• Advanced similarity measurement from content
• Efficient search acceleration methods