Defeasible Reasoning with Large Language Models - Initial Experiments and Future Directions

Grigoris Antoniou; Sotiris Batsakis

Defeasible Reasoning with Large Language Models - Initial Experiments and Future Directions

Research output: Contribution to journal › Conference article › peer-review

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.

Original language	English
Article number	7687
Number of pages	8
Journal	CEUR Workshop Proceedings
Volume	3485
Publication status	Published - 15 Sept 2023
Event	17th International Rule Challenge and 7th Doctoral Consortium @ RuleM+RR, RuleML+RR-Companion 2023 - Oslo, Norway Duration: 18 Sept 2023 → 20 Sept 2023 Conference number: 17

Access to Document

https://ceur-ws.org/Vol-3485/paper7687.pdfLicence: CC BY

Cite this

@article{66d96603d61e4e458d8472d7a7cc9a0b,

title = "Defeasible Reasoning with Large Language Models - Initial Experiments and Future Directions",

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.",

keywords = "Defeasible Reasoning, Large Language Models, Non-monotonic Reasoning",

author = "Grigoris Antoniou and Sotiris Batsakis",

note = "Funding Information: This research was funded by the Federal Ministry of Education and Research ?BMBF), Germany under the project LeibnizKILabor with grant No. 01DD20003. Publisher Copyright: {\textcopyright} 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).; 17th International Rule Challenge and 7th Doctoral Consortium @ RuleM+RR, RuleML+RR-Companion 2023 ; Conference date: 18-09-2023 Through 20-09-2023",

year = "2023",

month = sep,

day = "15",

language = "English",

volume = "3485",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - Defeasible Reasoning with Large Language Models - Initial Experiments and Future Directions

AU - Antoniou, Grigoris

AU - Batsakis, Sotiris

N1 - Conference code: 17

PY - 2023/9/15

Y1 - 2023/9/15

N2 - 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.

AB - 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.

KW - Defeasible Reasoning

KW - Large Language Models

KW - Non-monotonic Reasoning

UR - https://www.scopus.com/pages/publications/85174179837

UR - https://ceur-ws.org/Vol-3485/

M3 - Conference article

AN - SCOPUS:85174179837

SN - 1613-0073

VL - 3485

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

M1 - 7687

T2 - 17th International Rule Challenge and 7th Doctoral Consortium @ RuleM+RR, RuleML+RR-Companion 2023

Y2 - 18 September 2023 through 20 September 2023

ER -

Defeasible Reasoning with Large Language Models - Initial Experiments and Future Directions

Abstract

Access to Document

Other files and links

Fingerprint

Cite this