Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answeringby Xiaoming Zhang, Ming Wang, Xiaocui…
Finch: Prompt-guided Key-Value Cache Compressionby Giulio Corallo, Paolo PapottiFirst submitted to arxiv on: 31 Jul…
Better RAG using Relevant Information Gainby Marc Pickett, Jeremy Hartman, Ayan Kumar Bhowmick, Raquib-ul Alam,…
Evaluating Language Model Context Windows: A “Working Memory” Test and Inference-time Correctionby Amanda Dsouza, Christopher…
MammothModa: Multi-Modal Large Language Modelby Qi She, Junwen Pan, Xin Wan, Rui Zhang, Dawei Lu,…
Retrieval Meets Reasoning: Dynamic In-Context Editing for Long-Text Understandingby Weizhi Fei, Xueyan Niu, Guoqing Xie,…
Large Language Models for Automatic Milestone Detection in Group Discussionsby Zhuoxu Duan, Zhengye Yang, Samuel…
SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLMby Quandong Wang, Yuxuan Yuan,…
Recurrent Context Compression: Efficiently Expanding the Context Window of LLMby Chensen Huang, Guibo Zhu, Xuepeng…
Clustered Retrieved Augmented Generation (CRAG)by Simon Akesson, Frances A. SantosFirst submitted to arxiv on: 24…