Key Value
Key-value pair extraction focuses on efficiently identifying and extracting structured information from various data sources, including text, images, and databases, aiming to improve data organization and accessibility. Current research emphasizes leveraging large language models (LLMs) and transformer architectures, often incorporating techniques like attention mechanisms and fine-tuning on synthetic or real-world datasets to enhance accuracy and efficiency. This field is crucial for advancing information retrieval, document understanding, and database management, with applications ranging from medical diagnostics to efficient data storage and retrieval in large-scale systems.
Papers
RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs
Zhouxia Wang, Jiawei Zhang, Tianshui Chen, Wenping Wang, Ping Luo
Learning to Optimize LSM-trees: Towards A Reinforcement Learning based Key-Value Store for Dynamic Workloads
Dingheng Mo, Fanchao Chen, Siqiang Luo, Caihua Shan