Logo des Repositoriums
 

Large Language Models are Pattern Matchers: Editing Semi-Structured and Structured Documents with ChatGPT

Kurzanzeige
dc.contributor.authorWeber, Irene
dc.contributor.editorMarkus Böhm, Jürgen Wunderlich
dc.date.accessioned2024-10-01T10:15:40Z
dc.date.available2024-10-01T10:15:40Z
dc.date.issued2024
dc.description.abstractAbstract: Large Language Models (LLMs) offer numerous applications, the full extent of which is not yet understood. This paper investigates if LLMs can be applied for editing structured and semi-structured documents with minimal effort. Using a qualitative research approach, we conduct two case studies with ChatGPT and thoroughly analyze the results. Our experiments indicate that LLMs can effectively edit structured and semi-structured documents when provided with basic, straightforward prompts. ChatGPT demonstrates a strong ability to recognize and process the structure of annotated documents. This suggests that explicitly structuring tasks and data in prompts might enhance an LLM’s ability to understand and solve tasks. Furthermore, the experiments also reveal impressive pattern matching skills in ChatGPT. This observation deserves further investigation, as it may contribute to understanding the processes leading to hallucinations in LLMs.en
dc.identifier.doi10.18420/AKWI2024-001
dc.identifier.isbn978-3-88579-801-9
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/44648
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofAKWI Jahrestagung 2024
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-357
dc.subjectLLM
dc.subjectlarge language model
dc.subjectdocument processing
dc.subjectpattern matching
dc.subjectprompt engineering
dc.titleLarge Language Models are Pattern Matchers: Editing Semi-Structured and Structured Documents with ChatGPTen
dc.typeText/Conference Paper
gi.citation.endPage18
gi.citation.publisherPlaceBonn
gi.citation.startPage3
gi.conference.date09.-10.09.2024
gi.conference.locationHAW-Landshut
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
AKWI2024_01.pdf
Größe:
928.77 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P357 - AKWI Jahrestagung 2024 - Wissenschaft und Praxis: Gemeinsam die digitale Zukunft gestalten