Retrieval-Augmented Visual Document Understanding, Long Context RAG Performance of LLMs and More!

Vol.77 for Nov 04 - Nov 10, 2024

Stay Ahead of the Curve with the Latest Advancements and Discoveries in Information Retrieval.

This week’s newsletter highlights the following research:

1. Bridging Visual and Textual Document Understanding with Multi-modal Retrieval, from Bloomberg

2. Best Practices for Distilling Large Language Models into BERT for Web Search Ranking, from Tencent

3. Long Context RAG Performance of Large Language Models, from Databricks

4. A Pairwise Perspective on Softmax Loss for Robust Recommendation, from Zhejiang University

5. Efficient HTML Processing for RAG Systems, from Tan et al.

6. A Universal Framework for Multimodal Retrieval with Large Language Models, from NVIDIA

7. Rationale-Guided Retrieval Augmented Generation for Medical Question Answering, from Korea University

8. A Reasoning-Based Framework for Document Reranking with Large Language Models, from Salesforce AI Research

9. Efficient RAG Through Cost-Constrained Chunk Optimization and Dynamic Configuration, from NTU

10. A Comprehensive Assessment of LLMs in Recommendation, from Jiang et al.