Trustworthy and Efficient LLMs Meet Databases

TL;DR

This paper provides an overview of efforts to enhance trustworthiness and efficiency of large language models (LLMs), focusing on reducing hallucinations and meeting inference demands, with a special emphasis on their intersection with database technologies.

Contribution

It offers a comprehensive tutorial connecting LLM trustworthiness and efficiency improvements with database techniques, highlighting new opportunities and challenges at their intersection.

Findings

Summarizes current methods for reducing LLM hallucinations.

Explores the synergy between LLMs and databases.

Identifies future research directions in LLM-database integration.

Abstract

In the rapidly evolving AI era with large language models (LLMs) at the core, making LLMs more trustworthy and efficient, especially in output generation (inference), has gained significant attention. This is to reduce plausible but faulty LLM outputs (a.k.a hallucinations) and meet the highly increased inference demands. This tutorial explores such efforts and makes them transparent to the database community. Understanding these efforts is essential in harnessing LLMs in database tasks and adapting database techniques to LLMs. Furthermore, we delve into the synergy between LLMs and databases, highlighting new opportunities and challenges in their intersection. This tutorial aims to share with database researchers and practitioners essential concepts and strategies around LLMs, reduce the unfamiliarity of LLMs, and inspire joining in the intersection between LLMs and databases.