About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
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.