Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts

要旨

Pre-trained large language models ("LLMs") like GPT-3 can engage in fluent, multi-turn instruction-taking out-of-the-box, making them attractive materials for designing natural language interactions. Using natural language to steer LLM outputs ("prompting") has emerged as an important design technique potentially accessible to non-AI-experts. Crafting effective prompts can be challenging, however, and prompt-based interactions are brittle. Here, we explore whether non-AI-experts can successfully engage in "end-user prompt engineering" using a design probe—a prototype LLM-based chatbot design tool supporting development and systematic evaluation of prompting strategies. Ultimately, our probe participants explored prompt designs opportunistically, not systematically, and struggled in ways echoing end-user programming systems and interactive machine learning systems. Expectations stemming from human-to-human instructional experiences, and a tendency to overgeneralize, were barriers to effective prompt design. These findings have implications for non-AI-expert-facing LLM-based tool design and for improving LLM-and-prompt literacy among programmers and the public, and present opportunities for further research.

著者
J.D. Zamfirescu-Pereira
Berkeley, Berkeley, California, United States
Richmond Y.. Wong
Georgia Institute of Technology, Atlanta, Georgia, United States
Bjoern Hartmann
UC Berkeley, Berkeley, California, United States
Qian Yang
Cornell University, Ithaca, New York, United States
論文URL

https://doi.org/10.1145/3544548.3581388

動画

会議: CHI 2023

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2023.acm.org/)

セッション: Large Language Models

Hall C
6 件の発表
2023-04-25 23:30:00
2023-04-26 00:55:00