A Practical Guide to HNSW vs. Flat Indexes, Enhancing Lexical Retrieval with Dense Neighborhood Insights, and More!

Vol.69 for Sep 09 - Sep 15, 2024

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

This week’s newsletter highlights the following research:

1. A Practical Guide to HNSW vs. Flat Indexes, from Lin et al.

2. A Comprehensive Study of Ranking Models for Q&A Systems, from NVIDIA

3. Enhancing Lexical Retrieval with Dense Neighborhood Insights, from Kulkarni et al.

4. Optimizing Retrieval with Late Chunking, from Jina AI

5. A Systematic Exploration of Negative Sampling in Recommendation Research, from Ma et al.

6. Unifying Semantic Tokenization and Generative Recommendation, from Liu et al.

7. A Single-Pass Approach to Generation and Retrieval in Large Language Models, from Zhang et al.

8. Enhancing E-commerce Recommendations with Aspect-Based Carousel Headers, from Walmart

9. Enhancing Retrieval-Augmented Generation with Long-Term Memory for Complex Queries, from Qian et al.

10. An End-to-End Generative Recommender with Integrated Item Tokenization, from Liu et al.