Logo des Repositoriums
 

Engineering A Reliable Prompt For Generating Unit Tests - Prompt engineering for QA & QA for prompt engineering

dc.contributor.authorFaragó, David
dc.contributor.editorHerrmann, Andrea
dc.date.accessioned2024-02-05T10:39:26Z
dc.date.available2024-02-05T10:39:26Z
dc.date.issued2023
dc.description.abstractThis paper demonstrates Prompt Engineering (PE) on a running example: generating unit test cases for a given function. By iter atively adding further prompt patterns and measuring the robustness, correctness, and comprehensiveness of the AI’s output, multiple prompt patterns and their purpose and strength are investigated. We conclude that high robustness, correctness, and comprehensiveness is hard to achieve, and many prompt patterns (single prompt as well as patterns that span over a conversation) are necessary. More generally, quality assurance is a dominant part of PE and closely intertwined with the development part of PE. Thus traditional testing processes and stages do not adequately apply to QA for PE, and we suggest a PE process that covers the development and quality assurance of prompts as alternative.en
dc.identifier.issn0720-8928
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/43480
dc.language.isoen
dc.pubPlaceBonn
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofSoftwaretechnik-Trends Band 43, Heft 3
dc.relation.ispartofseriesSoftwaretechnik-Trends
dc.subjectprompt engineering
dc.subjecttest generation
dc.subjectLarge Language Models
dc.subjectquality
dc.titleEngineering A Reliable Prompt For Generating Unit Tests - Prompt engineering for QA & QA for prompt engineeringen
dc.typeText/Conference Paper
mci.conference.date15.-16.06.2023
mci.conference.locationPaderborn, Germany
mci.conference.sessiontitleTreffen der GI-Fachgruppe Test, Analyse und Verifikation von Software (TAV 48)
mci.reference.pages10-14

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
1_TAV48_Farago.pdf
Größe:
313.08 KB
Format:
Adobe Portable Document Format