[TMP-103] Prompt Design for Everyone: Interactive Grounding for Non-AI Experts in Large- Language Models

Contact person: Robin Welsch (robin.welsch@aalto.fi)

Internal Partners:

1. LMU Munich, Florian Müller, florian.mueller@um.ifi.lmu.de,
2. Aalto University, Robin Welsch, robin.welsch@aalto.fi

Generative models such as large language models (LLM) are a versatile AI tool for people from various domains, with varying backgrounds and goals. However, it is often challenging to formulate and refine suitable prompts that are the foundation for interaction with these models, especially for non-experts. To build human-centered AI interfaces, non-experts must be empowered to establish common ground when interacting with AI.

The aim of this project is to investigate how prompt-based AIs can establish a common ground of what is desirable on the user side and feasible on the model side. In this MP, motivated by a requirement analysis, we designed a study to find out how people varying in AI-expertise design prompts.

Results Summary

We have run a large-scale survey (1500 respondents) to identify use patterns as a function of AI-expertise and demographic data (Data will be made openly available soon). We are now designing a second study in which we re invite a set of participants varying in AI – expertise to gather their prompts in a set of representative interactive tasks. From these, we will derive design recommendations for Human-AI collaboration support for levels of AI expertise. We have published the study under pre-print and it has already gained more than 10 citations.

Tangible Outcomes

1. [arxiv] Gender, Age, and Technology Education Influence the Adoption and Appropriation of LLMs Fiona Draxler, Daniel Buschek, Mikke Tavast, Perttu Hämäläinen, Albrecht Schmidt, Juhi Kulshrestha, Robin Welsch https://arxiv.org/abs/2310.06556 
2. Data can be found here: https://osf.io/bdn9p/view_only=1a44dfd53cc1442a87bfc3f49560b112 
3.  A pre-registration for the demographic study: https://aspredicted.org/VCN_CCS