Improving Robustness, Inference Speed and Storage for Retrieval-Augmented Language Models, Aligning LLMs to Distinguish Fine-Grained Information for IR Tasks, and More!

Vol.20 for Oct 02 - Oct 08, 2023

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

This week’s newsletter highlights the following research:

1. Improving Specificity of Large Language Models for Information Retrieval via Reinforcement Learning from Contrastive Feedback, from Baidu

2. Retrieval-Augmented Dual Instruction Tuning: Retrofitting Models f…