Powered by OpenAIRE graph
Found an issue? Give us feedback
ZENODOarrow_drop_down
ZENODO
Event . 2024
License: CC BY
Data sources: Datacite
ZENODO
Event . 2024
License: CC BY
Data sources: Datacite
ZENODO
Event . 2024
License: CC BY
Data sources: Datacite
ZENODO
Event . 2024
License: CC BY
Data sources: Datacite
versions View all 4 versions
addClaim

Workshop Generative KI, LLMs und GPT bei digitalen Editionen

Workshop Generative AI, LLMs and GPT for digital editions
Authors: Czmiel, Alexander; Dumont, Stefan; Fischer, Franz; Pollin, Christopher; Sahle, Patrick; Schaßan, Torsten; Scholger, Martina; +4 Authors

Workshop Generative KI, LLMs und GPT bei digitalen Editionen

Abstract

Dieser Workshop konzentriert sich auf die Erforschung der Anwendungsmöglichkeiten und Herausforderungen von KI-basierten Anwendungen wie GPT und Large Language Models (LLMs) im Kontext digitaler Editionen. GPT-4, mindestens bis Juli 2023 das führende Modell, bietet erhebliche Potenziale, z.B. für die Umwandlung von unstrukturiertem Text in strukturierte Daten und die Erkennung von benannten Entitäten. Dennoch liefert es bislang noch unbefriedigende Ergebnisse, weshalb sorgfältige Überwachung und Feedbacksysteme unerlässlich sind. Die Integration von LLMs in Arbeitsabläufe und Webentwicklungsprojekte ist vielversprechend, erfordert jedoch noch konzeptionelle und dann auch technische Vorstudien. In Anbetracht der rasanten KI- und LLM-Entwicklungen lädt der Workshop dazu ein, zu experimentieren und Strategien für den effektiven Einsatz dieser Modelle in digitalen Editionsprojekten zu diskutieren.

Keywords

Artificial intelligence, Digital humanities

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average