App to App Retrieval
App-to-app retrieval focuses on efficiently and accurately retrieving relevant information from large datasets, particularly within the context of augmented generation models. Current research emphasizes improving retrieval methods through techniques like contrastive learning, recursive abstractive processing, and the incorporation of derived features or semantic similarity searches, often within hierarchical memory structures. These advancements are crucial for enhancing various applications, including fact-checking, question answering, recommendation systems, and robotics, by enabling more effective use of large language models and multimodal data. The ultimate goal is to create more robust and efficient systems capable of handling increasingly complex information retrieval tasks.
Papers
Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion
Muzhi Li, Cehao Yang, Chengjin Xu, Xuhui Jiang, Yiyan Qi, Jian Guo, Ho-fung Leung, Irwin King
Retrieval of sun-induced plant fluorescence in the O$_2$-A absorption band from DESIS imagery
Jim Buffat, Miguel Pato, Kevin Alonso, Stefan Auer, Emiliano Carmona, Stefan Maier, Rupert Müller, Patrick Rademske, Uwe Rascher, Hanno Scharr
Problem-Oriented Segmentation and Retrieval: Case Study on Tutoring Conversations
Rose E. Wang, Pawan Wirawarn, Kenny Lam, Omar Khattab, Dorottya Demszky
Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models
Dongrui Han, Mingyu Cui, Jiawen Kang, Xixin Wu, Xunying Liu, Helen Meng
Leveraging Retrieval-Augmented Generation for Persian University Knowledge Retrieval
Arshia Hemmat, Kianoosh Vadaei, Mohammad Hassan Heydari, Afsaneh Fatemi
Exploring Knowledge Boundaries in Large Language Models for Retrieval Judgment
Zhen Zhang, Xinyu Wang, Yong Jiang, Zhuo Chen, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang