Empowering Smaller LLMs in Passage Re-Ranking, GPT-4 as a Reliable Evaluator for RAG Applications, and More!

Vol.58 for Jun 24 - Jun 30, 2024

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

This week’s newsletter highlights the following research:

1. Learnable Late-Interaction Models for Efficient and Accurate Information Retrieval, from Google

2. Gaming the AI: How Crafted Content Can Hijack LLM-Powered Search Results, from ETH Zurich

3. Dynamic Text Segmentation for Enhanced Retrieval in RAG Systems, from Duarte et al.

4. Improving Collaborative Filtering with Simplified Sampled Softmax Cross-Entropy, from Visa

5. Automating Quality Assessment in Retrieval-Augmented Generation with GPT-4, from Visa

6. Efficient Listwise Passage Reranking via Embedding Compression, from Liu et al.

7. Empowering Smaller LLMs in Passage Re-Ranking through Pre-Filtering, from Polytechnique Montréal

8. Efficient Online Hyper-Parameter Optimization for RAG Systems, from Microsoft

9. Decomposed and Distilled Large Language Models for Efficient and Accurate Semantic Search, from Ant Group

10. Accelerating LLM Reranking with Single-Token Logits, from Reddy et al.

---