Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Conference object . 2025
License: CC BY
Data sources: ZENODO
ZENODO
Article . 2025
License: CC BY
Data sources: Datacite
ZENODO
Article . 2025
License: CC BY
Data sources: Datacite
DBLP
Conference object
Data sources: DBLP
versions View all 3 versions
addClaim

Prompt-Engineering und Hermeneutik – Best Practices für die historische und qualitative Forschung

Authors: Möbus, Dennis; Vu, Binh; Bayerschmidt, Philipp;

Prompt-Engineering und Hermeneutik – Best Practices für die historische und qualitative Forschung

Abstract

Der Workshop widmet sich dem Design von Prompts für Large-Language-Models (LLM) und richtet sich vorrangig (aber nicht nur) an Vertreter:innen qualitativ-hermeneutisch arbeitender Disziplinen. Es werden unterschiedliche Prompting-Methoden (Zero-/One-/Few-Shot-Learning, Chain-of-Thought-Prompting u.a.) an verschiedenen LLMs getestet, um Fragen zwischen Informationsextraktion und maschineller Interpretation zu behandeln. Die Datengrundlage werden lebensgeschichtliche Interviews aus dem Bestand von Oral-History.Digital und Briefserien aus dem 19. und 20. Jahrhundert sein. Werden zunächst etablierte Methoden aus den Bereichen maschinelles Lernen und Natural Language Processing (NLP) wie Topic Modeling und Named Entity Recognition (NER) adaptiert, wird in einem zweiten Schritt das generative Potential der LLMs genutzt, um Textexzerpte und Kurzbiographien aus den Quellen herauszuarbeiten. Am zweiten Tag gilt es, durch das Entwerfen von Templates in den Bereich maschineller Interpretation vorzudringen. Vorkenntnisse sind nicht erforderlich, zur Teilnahme am Hands-on-Workshop ist ein eigenes digitales Endgerät (vorzugsweise Laptop) erforderlich.

Related Organizations
Keywords

Paper, LLM, Prompt Engineering, KI, Strukturanalyse, Text Mining, Prompting, Annotieren, Entdeckung, Modellierung, Text, DHd2025, Prompt, Prompt Design, Biographieforschung, Geschichtswissenschaft, Workshop, Inhaltsanalyse

  • 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
Green