Rethinking RAG in the Era of Long-Context LLMs, A Lightweight Framework for Combining Domain Experts, and More!

Vol.68 for Sep 02 - Sep 08, 2024

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

This week’s newsletter highlights the following research:

1. Retrieval-Augmented Generation for Superior Long-Context Question Answering, from NVIDIA

2. A Near Real-Time Ranking Platform for Modern E-Commerce, from Zalando

3. A Method for Automated Task-Specific Dataset Creation and Model Fine-Tuning, from Ziegler et al.

4. A Lightweight Framework for Combining Domain Experts in Information Retrieval, from Lee et al.

5. Dynamically Determining Compression Rates for Improved RAG Performance, from Zhang et al.

6. A Comprehensive Study of Pooling and Attention Strategies for Optimizing LLM-Based Embedding Models, from HKUST

7. Unbiasing Short-Video Recommenders through Causal Inference, from Dong et al.

8. Non-Parametric Embedding Fine-Tuning for Improved k-NN Retrieval, from Zeighami et al.

9. A High-Performance Batch Query Architecture for Industrial-Scale Recommendation Systems, from Zhang et al.

10. Correcting Stale Embeddings for Computationally Efficient Dense Retrieval, from Google DeepMind