Retrieval Performance
Retrieval performance, crucial for applications like question answering and search engines, focuses on efficiently and accurately retrieving relevant information from large datasets. Current research emphasizes improving semantic understanding in retrieval through advanced embedding models (e.g., those leveraging multi-vector representations or multimodal fusion) and optimizing search algorithms (like those employing adaptive compression or hybrid search strategies). These advancements are significant because they directly impact the accuracy and efficiency of numerous AI systems, particularly those employing retrieval-augmented generation, leading to improved user experience and more reliable information access.
Papers
CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity
Jintao Liu, Ruixue Ding, Linhao Zhang, Pengjun Xie, Fie Huang
AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning
Mohammad Reza Rezaei, Maziar Hafezi, Amit Satpathy, Lovell Hodge, Ebrahim Pourjafari
Lessons Learned on Information Retrieval in Electronic Health Records: A Comparison of Embedding Models and Pooling Strategies
Skatje Myers, Timothy A. Miller, Yanjun Gao, Matthew M. Churpek, Anoop Mayampurath, Dmitriy Dligach, Majid Afshar
Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
Benjamin Clavié, Antoine Chaffin, Griffin Adams
Lab-AI -- Retrieval-Augmented Language Model for Personalized Lab Test Interpretation in Clinical Medicine
Xiaoyu Wang, Haoyong Ouyang, Balu Bhasuran, Xiao Luo, Karim Hanna, Mia Liza A. Lustria, Zhe He
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Zhenhua Han, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, Lili Qiu