The More Is Not the Merrier: Effects of Prompt Engineering on the Quality of Ideas Generated By GPT-3

Simple item page
dc.contributor.authorMemmert, Lucas
dc.contributor.authorCvetkovic, Izabel
dc.contributor.authorBittner, Eva
dc.date.accessioned2023-12-26T18:54:24Z
dc.date.available2023-12-26T18:54:24Z
dc.date.issued2024-01-03
dc.identifier.doi10.24251/HICSS.2024.903
dc.identifier.isbn978-0-9981331-7-1
dc.identifier.other1e896519-a8d9-40e9-9057-3137194b0833
dc.identifier.urihttps://hdl.handle.net/10125/107289
dc.language.isoeng
dc.relation.ispartofProceedings of the 57th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectGenerative and Conversational AI in Information Systems Research and Education: Opportunities and Challenges
dc.subjectbrainstorming
dc.subjectgenerative language model
dc.subjectgpt-3
dc.subjecthuman-ai collaboration
dc.subjectprompt engineering
dc.titleThe More Is Not the Merrier: Effects of Prompt Engineering on the Quality of Ideas Generated By GPT-3
dc.typeConference Paper
dc.type.dcmiText
dcterms.abstractGenerative language models (GLM) like GPT-3 can support humans in creative tasks. Such systems are capable of generating free-text output based on a provided input prompt. Given the outputs’ sensitivity to the prompt, many techniques for prompt engineering were proposed both anecdotally in social media and increasingly in literature. It is, however, unclear if and how such a system and such techniques can be employed in creative contexts such as for generating ideas. In our study, we investigate the effects of using six prompt engineering techniques. For each combination of techniques, we have GPT-3 generate ideas for an exemplary scenario. The ideas are rated according to novelty and value. We report on the effects of the (combinations of) prompt engineering techniques. With our study, we contribute to the emerging field of prompt engineering and shed light on supporting idea generation with GLMs, showing a pathway to embedded GLM capabilities.
dcterms.extent10 pages
prism.startingpage7520

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0734.pdf
Size:
972.3 KB
Format:
Adobe Portable Document Format
Download

Collections

Generative and Conversational AI in Information Systems Research and Education: Opportunities and Challenges