Exploring Prompt Engineering Practices in the Enterprise

no code implementations • 13 Mar 2024 • Michael Desmond, Michelle Brachman

Creating effective prompts requires skill and knowledge, as well as significant iteration in order to determine model behavior, and guide the model to accomplish a particular goal.

Prompt Engineering

A No-Code Low-Code Paradigm for Authoring Business Automations Using Natural Language

no code implementations • 15 Jul 2022 • Michael Desmond, Evelyn Duesterwald, Vatche Isahagian, Vinod Muthusamy

We propose a paradigm for the construction of business automations using natural language.

Language Modelling Large Language Model

Label Noise in Context

no code implementations • ACL 2020 • Michael Desmond, Catherine Finegan-Dollak, Jeff Boston, Matt Arnold

Label noise{---}incorrectly or ambiguously labeled training examples{---}can negatively impact model performance.

text-classification Text Classification

Towards Automating the AI Operations Lifecycle

no code implementations • 28 Mar 2020 • Matthew Arnold, Jeffrey Boston, Michael Desmond, Evelyn Duesterwald, Benjamin Elder, Anupama Murthi, Jiri Navratil, Darrell Reimer

Today's AI deployments often require significant human involvement and skill in the operational stages of the model lifecycle, including pre-release testing, monitoring, problem diagnosis and model improvements.