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 . 2024
License: CC BY
Data sources: ZENODO
ZENODO
Article . 2024
License: CC BY
Data sources: Datacite
ZENODO
Article . 2024
License: CC BY
Data sources: Datacite
DBLP
Conference object
Data sources: DBLP
versions View all 3 versions
addClaim

»LLMs for everything?« Potentiale und Probleme der Anwendung von In-Context-Learning für die Computational Literary Studies

Authors: Pichler, Axel; Reiter, Nils;

»LLMs for everything?« Potentiale und Probleme der Anwendung von In-Context-Learning für die Computational Literary Studies

Abstract

Große Sprachmodelle, sogenannte ›Large Language Models‹ (LLMs), zeigen ab einer bestimmten Größe ›emergent abilites‹, durch die sie sich von Ihren Vorläufern unterscheiden. Zu diesen Fähigkeiten zählt insbesondere die Möglichkeit des sogenannten In-Context-Learnings (ICL), das sich von den traditionellen Formen des (selbst)überwachten Lernens unterscheidet: Anstelle ein vortrainiertes Model mithilfe von fragestellungsspezifischen Daten feinabzustimmen, arbeitet man beim ICL mit natürlichsprachlichen Eingaben – sogenannten ›Prompts‹ –, welche aus einer Beschreibung der auszuführenden Aufgabe und/oder Beispielen derselben bestehen. Im Rahmen unseres Vortrages wollen wir Potential und Probleme dieser Technik für die Computational Literary Studies (CLS) ausloten. Dafür versuchen wir die Resultate von Andrew Pipers Studie »Can we wrong?«, die sich der Rolle von Generalisierungen in den Literary Studies widmet, auf Basis von OpenAIs text-davinci-003-LLM mithilfe von ICL zu reproduzieren bzw. zu übertreffen. Ausgehend von den verhältnismäßig niedrigen Accuracy- und F1-Scores, die wir dabei erzielten, reflektieren wir die gegenwärtigen Einsatzmöglichkeiten von ICL in den CLS.

Related Organizations
Keywords

Paper, Large Language Models, Theoretisierung, Vortrag, Annotieren, DHd2024, Modellierung, Computational Literary Studies, In-Context-Learning

  • 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).
    1
    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!
1
Average
Average
Average
Green