Abstract-level Deductive Reasoning for Pre-trained Language Models

Xin Wu; Yi Cai; Ho-fung Leung

COLING 2024main0 citations

Abstract-level Deductive Reasoning for Pre-trained Language Models

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%).

BibTeX

@inproceedings{wu-etal-2024-abstract,
    title = "Abstract-level Deductive Reasoning for Pre-trained Language Models",
    author = "Wu, Xin  and
      Cai, Yi  and
      Leung, Ho-fung",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.6/",
    pages = "70--76"
}