Agentic Information Retrieval, A Comparative Study of Semantic vs. Fixed-Size Strategies, and More!

Vol.74 for Oct 14 - Oct 20, 2024

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

This week’s newsletter highlights the following research:

1. Agentic Information Retrieval as the Next Generation of IR Systems, from SJTU

2. A Novel Approach to Extracting Rich Embeddings from Mixture-of-Experts LLMs, from UMD

3. Starbucks Method for Efficient and Effective Embedding Model Training, from Zhuang et al.

4. Enhancing Semi-Structured Retrieval with Knowledge-Aware Query Expansion, from Xia et al.

5. A Comparative Study of Semantic vs. Fixed-Size Strategies, from Qu et al.

6. Enhancing Encoder-Only Transformers for Next-Item Prediction in Session-Based Recommenders, from Redjdal et al.

7. A Framework for Integrating Visual, Textual, and Graph Data in LLM-Based Recommenders, from Walmart

8. Layer-of-Thoughts Framework for Advanced Information Retrieval, from ROIS-DS

9. Language Model Agents for a Healthier Digital Public Sphere, from Lazar et al.

10. Adaptive-Note RAG for Improved Information Integration, from Wang et al.