Imagen de Portada

Unstructured Data Analysis using LLMs: A Comprehensive Benchmark

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Deng, Qiyan, Li, Jianhui, Chai, Chengliang, Liu, Jinqi, She, Junzhi, Jin, Kaisen, Sun, Zhaoze, Deng, Yuhao, Yuan, Jia, Yuan, Ye, Wang, Guoren, Cao, Lei
Formato:	Preprint
Publicado:	2025
Materias:	Databases
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

QUEST: Query Optimization in Unstructured Document Analysis
por: Sun, Zhaoze, et al.
Publicado: (2025)

Graph-Based Feature Augmentation for Predictive Tasks on Relational Datasets
por: Qiao, Lianpeng, et al.
Publicado: (2025)

StreamTGN: A GPU-Efficient Serving System for Streaming Temporal Graph Neural Networks
por: Zhang, Lingling, et al.
Publicado: (2026)

Multivariate Time Series Cleaning under Speed Constraints
por: Zhang, Aoqian, et al.
Publicado: (2024)

Analytical Queries for Unstructured Data
por: Kang, Daniel
Publicado: (2025)

AutoCE: An Accurate and Efficient Model Advisor for Learned Cardinality Estimation
por: Zhang, Jintao, et al.
Publicado: (2024)

Task Cascades for Efficient Unstructured Data Processing
por: Shankar, Shreya, et al.
Publicado: (2026)

The Dawn of Natural Language to SQL: Are We Fully Ready?
por: Li, Boyan, et al.
Publicado: (2024)

PACE: Poisoning Attacks on Learned Cardinality Estimation
por: Zhang, Jintao, et al.
Publicado: (2024)

Multi-Objective Agentic Rewrites for Unstructured Data Processing
por: Wei, Lindsey Linxi, et al.
Publicado: (2025)

A Case for Computing on Unstructured Data
por: Sadia, Mushtari, et al.
Publicado: (2025)

UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data
por: Weng, Han, et al.
Publicado: (2025)

Accelerating Approximate Analytical Join Queries over Unstructured Data with Statistical Guarantees
por: Zhu, Yuxuan, et al.
Publicado: (2026)

Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks
por: Li, Xunkai, et al.
Publicado: (2024)

Not All Instances Are Equally Valuable: Towards Influence-Weighted Dataset Distillation
por: Deng, Qiyan, et al.
Publicado: (2025)

CHASE: A Native Relational Database for Hybrid Queries on Structured and Unstructured Data
por: Ma, Rui, et al.
Publicado: (2025)

FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data
por: Wang, Ziting, et al.
Publicado: (2025)

Benchmarking Time Series Databases with IoTDB-Benchmark for IoT Scenarios
por: Liu, Rui, et al.
Publicado: (2019)

LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning
por: Lin, Xiaotian, et al.
Publicado: (2025)

MCI: A Maximal Clique Index for Efficient Arbitrary-Filtered Approximate Nearest Neighbor Search
por: Ye, Xiaowei, et al.
Publicado: (2026)

OpenFGL: A Comprehensive Benchmark for Federated Graph Learning
por: Li, Xunkai, et al.
Publicado: (2024)

Relational Deep Dive: Error-Aware Queries Over Unstructured Data
por: Chao, Daren, et al.
Publicado: (2025)

LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data
por: Hu, Chuxuan, et al.
Publicado: (2025)

LLM-Driven Online Aggregation for Unstructured Text Analytics
por: Hui, Chao, et al.
Publicado: (2026)

Process Mining for Unstructured Data: Challenges and Research Directions
por: Koschmider, Agnes, et al.
Publicado: (2023)

Optimal $(α,β)$-Dense Subgraph Search in Bipartite Graphs
por: Zhang, Yalong, et al.
Publicado: (2025)

DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning
por: Hu, Yunhai, et al.
Publicado: (2026)

Cortex AISQL: A Production SQL Engine for Unstructured Data
por: Liskowski, Paweł, et al.
Publicado: (2025)

Continuous Prompts: LLM-Augmented Pipeline Processing over Unstructured Streams
por: Chen, Shu, et al.
Publicado: (2025)

Effective Bug Detection in Graph Database Engines: An LLM-based Approach
por: Wu, Jiayi, et al.
Publicado: (2024)

DW-Bench: Benchmarking LLMs on Data Warehouse Graph Topology Reasoning
por: Ahmed, Ahmed G. A. H, et al.
Publicado: (2026)

MCTS-SQL: Light-Weight LLMs can Master the Text-to-SQL through Monte Carlo Tree Search
por: Yuan, Shuozhi, et al.
Publicado: (2025)

Version Control System for Data with MatrixOne
por: Gou, Hongshen, et al.
Publicado: (2026)

FB$^+$-tree: A Memory-Optimized B$^+$-tree with Latch-Free Update
por: Chen, Yuan, et al.
Publicado: (2025)

RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
por: Yuan, Bo, et al.
Publicado: (2026)

BPI: A Novel Efficient and Reliable Search Structure for Hybrid Storage Blockchain
por: Zhao, Xinkui, et al.
Publicado: (2025)

MMTS-BENCH: A Comprehensive Benchmark for Time Series Understanding and Reasoning
por: Yin, Yao, et al.
Publicado: (2026)

AgenticData: An Agentic Data Analytics System for Heterogeneous Data
por: Sun, Ji, et al.
Publicado: (2025)

PM4Py.LLM: a Comprehensive Module for Implementing PM on LLMs
por: Berti, Alessandro
Publicado: (2024)

CardOOD: Robust Query-driven Cardinality Estimation under Out-of-Distribution
por: Li, Rui, et al.
Publicado: (2024)