Back to Main Conference 2024
LREC-COLING 2024main

Abstract-level Deductive Reasoning for Pre-trained Language Models

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

DOI:10.63317/5mr3ve2dcoj4

Abstract

Pre-trained Language Models have been shown to be able to emulate deductive reasoning in natural language. However, PLMs are easily affected by irrelevant information (e.g., entity) in instance-level proofs when learning deductive reasoning. To address this limitation, we propose an Abstract-level Deductive Reasoner (ADR). ADR is trained to predict the abstract reasoning proof of each sample, which guides PLMs to learn general reasoning patterns rather than instance-level knowledge. Experimental results demonstrate that ADR significantly reduces the impact of PLMs learning instance-level knowledge (over 70%).

Details

Paper ID
lrec2024-main-0006
Pages
pp. 70-76
BibKey
wu-etal-2024-abstract
Editor
N/A
Publisher
European Language Resources Association (ELRA) and ICCL
ISSN
2522-2686
ISBN
979-10-95546-34-4
Conference
Joint International Conference on Computational Linguistics, Language Resources and Evaluation
Location
Turin, Italy
Date
20 May 2024 25 May 2024

Authors

  • XW

    Xin Wu

  • YC

    Yi Cai

  • HL

    Ho-fung Leung

Links