Langanzeige der Metadaten
DC ElementWertSprache
dc.contributor.authorSeifert, Daniel-
dc.contributor.authorJöckel, Lisa-
dc.contributor.authorHonroth, Thorsten-
dc.contributor.authorTrendowicz, Adam-
dc.contributor.authorJedlitschk, Andreas-
dc.contributor.authorCiolkowski, Marcus-
dc.date.accessioned2024-08-06T12:55:50Z-
dc.date.available2024-08-06T12:55:50Z-
dc.date.issued2024-08-01-
dc.identifier.urihttps://fordatis.fraunhofer.de/handle/fordatis/411-
dc.identifier.urihttp://dx.doi.org/10.24406/fordatis/359-
dc.description.abstractThis is the data for the paper "Can Large Language Models (LLMs) Compete with Human Requirements Reviewers? – Replication of an Inspection Experiment on Requirements Documents". It contains the source code of the experiment to make our work transparent and reproducible. Furthermore, it contains the evaluation results.en
dc.language.isoenen
dc.rights.urihttps://creativecommons.org/licenses/by-sa/4.0/en
dc.subjectLarge Language Models (LLMs)en
dc.subjectRequirements Engineeringen
dc.subjectInspection Experimenten
dc.subjectPythonen
dc.subjectQuality Assessmenten
dc.subject.ddcDDC::000 Informatik, Informationswissenschaft, allgemeine Werkeen
dc.titleCan Large Language Models (LLMs) compete with Human Requirement Reviewers? - Replication of an Inspection Experiment on Requirements Documentsen
dc.typeSource Codeen
dc.contributor.funderBundesministerium für Bildung und Forschung BMBF (Deutschland)en
dc.description.technicalinformationThe code is written in python. For each experiment there is one jupyter notebook. We used OpenAI models and open source models. The open source models were run on our infrastructure. To run the code using the open source models, it must be adapted to the infrastructure you have access to.en
fordatis.groupIUK-Technologieen
fordatis.instituteIESE Fraunhofer-Institut für Experimentelles Software Engineeringen
fordatis.rawdatafalseen
fordatis.sponsorship.projectid01IS23016Den
fordatis.sponsorship.projectnameDeepQuali - Anwendung von Deep Learning auf Software-Repositories zur Qualitätsbewertungen
fordatis.sponsorship.projectacronymDeepQualien
Enthalten in den Sammlungen:Fraunhofer-Institut für Experimentelles Softwareengineering IESE

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
profes24_published_data.zipSource code and evaluation results434,56 kBZIPÖffnen/Download
Zur Kurzanzeige


Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons