The Crucial Role of Prompts in Zero-Shot LLM Ranking, Evaluating Retrieval-Augmented Code Generation, and More!

Vol.57 for Jun 17 - Jun 23, 2024

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

This week’s newsletter highlights the following research:

1. Training IR Models with Minimal Labels via Prompt-Optimized Query Synthesis, from Xian et al.

2. Probing the Interplay of Parametric and Non-Parametric Memory in RAG Language Models, from UMass Amherst

3. Prompt Engineering's Impact on Zero-Shot LLM Ranking Effectiveness, from The University of Queensland

4. A Systematic Analysis of Retrieval-Augmented Code Generation, from Wang et al.

5. Benchmarking Long-Context Language Models for Real-World Tasks, from Google DeepMind

6. A Tournament-Inspired Approach for Zero-Shot Document Ranking with Large Language Models, from Renmin University

7. Multifaceted Criteria for Determining Retrieval Need in Augmented Language Generation, from Fudan University

8. An LLM-based reranking Approach for Balancing Accuracy, Diversity and Fairness, from CityU

9. LLM-Guided Reinforcement Learning for Novel Item Recommendation in Large-Scale Systems, from Microsoft

10. Automating Prompt Engineering for Zero-Shot Passage Relevance Ranking, from Jin et al.