Antoniou, G.; Batsakis, S.: Defeasible Reasoning with Large Language Models - Initial Experiments and Future Directions. In: Vanthienen, Jan; Kliegr, Tomáš; Fodor, Paul; Lanti, Davide; Arndt, Dörthe; Kostylev, Egor V.; Mitsikas, Theodoros; Soylu, Ahmet (Eds.): RuleML+RR-Companion 2023: RuleML+RR Challenge and Doctoral Consortium 2023 : proceedings of the 17th International Rule Challenge and 7th Doctoral Consortium @ RuleML+RR 2023 co-located with 19th Reasoning Web Summer School (RW 2023) and 15th DecisionCAMP 2023 as part of Declarative AI 2023. Aachen, Germany : RWTH Aachen, 2023 (CEUR workshop proceedings ; 3485), 7687.
Abstract: | |
As Large Language Models gain prominence in the AI landscape, it is essential to understand their capabilities and limitations, among others in terms of reasoning. This paper is a first step towards understanding the capabilities in terms of defeasible rule-based reasoning. It presents results of initial experiments and discussed future research directions. | |
License of this version: | CC BY 4.0 Unported |
Document Type: | BookPart |
Publishing status: | publishedVersion |
Issue Date: | 2023 |
Appears in Collections: | Forschungszentren |
pos. | country | downloads | ||
---|---|---|---|---|
total | perc. | |||
1 | Germany | 7 | 70.00% | |
2 | United States | 2 | 20.00% | |
3 | China | 1 | 10.00% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.