A Next-Generation Encoder for Fast and Efficient NLP, LLMs for Real-World Recommender Systems, and More!

Vol.83 for Dec 16 - Dec 22, 2024

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

This week’s newsletter highlights the following research:

1. ModernBERT: A Next-Generation Encoder for Fast and Efficient Natural Language Processing, from Warner et al.

2. Token-Based Knowledge Assessment for Optimizing RAG Systems, from Naver

3. A Systematic Survey of LLM-Enhanced Recommender Systems, from Liu et al.

4. Disentangling Position Bias in Retrieval-Augmented Generation, from Snowflake AI Research

5. A Comprehensive Survey of LLM-based Embedding Models, from Tao et al.

6. A Comparative Study of Retrieval Strategies and Prompt Engineering, from Papadimitriou et al.

7. Bridging Visual and Textual Understanding in Multi-Document QA, from Adobe

8. Investigating Mixture of Experts in Dense Retrieval, from UNIMIB

9. A Comprehensive Analysis of Mamba Models for Text Reranking, from the University of Utah

10. Improving Passage Ranking Efficiency Through Long-Context LLM Full Ranking, from Liu et al.