Explore the latest research on scaling laws for dense retrieval in this 15-minute conference talk presented at SIGIR 2024. Delve into the findings of authors Yan Fang, Jingtao Zhan, Qingyao Ai, Jiaxin Mao, Weihang Su, Jia Chen, and Yiqun Liu as they discuss their work on Dense Retrieval 1 (T2.1). Gain insights into the scaling behaviors and performance improvements of dense retrieval models as they increase in size and complexity. Learn about the implications of these scaling laws for the development and optimization of information retrieval systems.
Overview
Syllabus
SIGIR 2024 T2.1 [fp] Scaling Laws For Dense Retrieval
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
Dimension Importance Estimation for Dense Information Retrieval - Tutorial 2.1
-
Negative Sampling Techniques for Dense Passage Retrieval in a Multilingual Setting - Lecture 4
-
Graded Relevance Scoring of Written Essays with Dense Retrieval - Tutorial 2.1
-
Leveraging LLMs for Unsupervised Dense Retriever Ranking - Dense Retrieval 1
-
Unsupervised Cross-Domain Image Retrieval with Semantic-Attended Mixture-of-Experts
-
Generative Retrieval via Term Set Generation - The Future of Search with LLMs
