Publication
INFORMS 2023
Talk

Safe Rl Prompting for Llms for Solving Data Management Challenges

Abstract

We consider the problem of usage of Large Language Models (LLMs) for data management tasks such as imputation and error detection. As task complexity increases as well as the need for accurate responses, so does the need for well-crafted prompts, which allow LLMs to learn in context. We propose to formulate the problem of prompt tuning as an RL problem. Moreover, we intend to craft prompting in a safe way avoiding dangerous decisions and finally getting Safe RL prompting for LLMs to tackle data management task challenges.

Date

Publication

INFORMS 2023

Authors

Topics

Share