Explore a cutting-edge conference talk on zero-shot ranking using Large Language Models (LLMs) in information retrieval. Delve into the setwise approach presented by authors Shengyao Zhuang, Honglei Zhuang, Bevan Koopman, and Guido Zuccon, which aims to enhance both effectiveness and efficiency in search ranking tasks. Learn how this innovative method leverages LLMs to improve search results without the need for task-specific training data. Gain insights into the potential applications and implications of this research for the future of search technology and information retrieval systems.
Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models - Session M1.1
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
SIGIR 2024 M1.1 [fp] Setwise Approach for Effective & Highly Efficient Zero-shot Ranking with LLMs
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
Large Language Models with Semantic Search
-
Leveraging LLMs for Unsupervised Dense Retriever Ranking - Dense Retrieval 1
-
Search Engine for Machines: Unified Ranking for Multi-Retrieval-Augmented LLMs - Lecture 1
-
GUITAR: Gradient Pruning toward Fast Neural Ranking - Efficiency for Search
-
Revisiting Document Expansion and Filtering for Effective First-Stage Retrieval - Lecture 3
-
Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback - Lecture 1
