Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximizationby Hamed Zamani, Michael BenderskyFirst submitted to…
Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documentsby Evgenii Kortukov, Alexander Rubinstein,…
iRAG: Advancing RAG for Videos with an Incremental Approachby Md Adnan Arefeen, Biplob Debnath, Md…
LongEmbed: Extending Embedding Models for Long Context Retrievalby Dawei Zhu, Liang Wang, Nan Yang, Yifan…
Position Engineering: Boosting Large Language Models through Positional Information Manipulationby Zhiyuan He, Huiqiang Jiang, Zilong…
Observations on Building RAG Systems for Technical Documentsby Sumit Soman, Sujoy RoychowdhuryFirst submitted to arxiv…
Towards a Robust Retrieval-Based Summarization Systemby Shengjie Liu, Jing Wu, Jingyuan Bao, Wenyi Wang, Naira…
JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuningby Anique Tahir, Lu Cheng, Huan LiuFirst…
Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries…
Improving Medical Multi-modal Contrastive Learning with Expert Annotationsby Yogesh Kumar, Pekka MarttinenFirst submitted to arxiv…