The Effect of Education in Prompt Engineering: Evidence from Journalists

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bashardoust, Amirsiavosh, Feng, Yuanjun, Geissler, Dominique, Feuerriegel, Stefan, Shrestha, Yash Raj
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917779532152832
author Bashardoust, Amirsiavosh
Feng, Yuanjun
Geissler, Dominique
Feuerriegel, Stefan
Shrestha, Yash Raj
author_facet Bashardoust, Amirsiavosh
Feng, Yuanjun
Geissler, Dominique
Feuerriegel, Stefan
Shrestha, Yash Raj
contents Large language models (LLMs) are increasingly used in daily work. In this paper, we analyze whether training in prompt engineering can improve the interactions of users with LLMs. For this, we conducted a field experiment where we asked journalists to write short texts before and after training in prompt engineering. We then analyzed the effect of training on three dimensions: (1) the user experience of journalists when interacting with LLMs, (2) the accuracy of the texts (assessed by a domain expert), and (3) the reader perception, such as clarity, engagement, and other text quality dimensions (assessed by non-expert readers). Our results show: (1) Our training improved the perceived expertise of journalists but also decreased the perceived helpfulness of LLM use. (2) The effect on accuracy varied by the difficulty of the task. (3) There is a mixed impact of training on reader perception across different text quality dimensions.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12320
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Effect of Education in Prompt Engineering: Evidence from Journalists
Bashardoust, Amirsiavosh
Feng, Yuanjun
Geissler, Dominique
Feuerriegel, Stefan
Shrestha, Yash Raj
Human-Computer Interaction
Large language models (LLMs) are increasingly used in daily work. In this paper, we analyze whether training in prompt engineering can improve the interactions of users with LLMs. For this, we conducted a field experiment where we asked journalists to write short texts before and after training in prompt engineering. We then analyzed the effect of training on three dimensions: (1) the user experience of journalists when interacting with LLMs, (2) the accuracy of the texts (assessed by a domain expert), and (3) the reader perception, such as clarity, engagement, and other text quality dimensions (assessed by non-expert readers). Our results show: (1) Our training improved the perceived expertise of journalists but also decreased the perceived helpfulness of LLM use. (2) The effect on accuracy varied by the difficulty of the task. (3) There is a mixed impact of training on reader perception across different text quality dimensions.
title The Effect of Education in Prompt Engineering: Evidence from Journalists
topic Human-Computer Interaction
url https://arxiv.org/abs/2409.12320