@inproceedings{lee-etal-2025-entailment,
    title = "Entailment-Preserving First-order Logic Representations in Natural Language Entailment",
    author = "Lee, Jinu  and
      Liu, Qi  and
      Ma, Runzhi  and
      Han, Vincent  and
      Wang, Ziqi  and
      Ji, Heng  and
      Hockenmaier, Julia",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.286/",
    pages = "5729--5742",
    ISBN = "979-8-89176-251-0",
    abstract = "First-order logic (FOL) is often used to represent logical entailment, but determining natural language (NL) entailment using FOL remains a challenge. To address this, we propose the Entailment-Preserving FOL representations (EPF) task and introduce reference-free evaluation metrics for EPF (Entailment-Preserving Rate (EPR) family). In EPF, one should generate FOL representations from multi-premise NL entailment data (e.g., EntailmentBank) so that the automatic prover{'}s result preserves the entailment labels. Furthermore, we propose a training method specialized for the task, iterative learning-to-rank, which trains an NL-to-FOL translator by using the natural language entailment labels as verifiable rewards. Our method achieves a 1.8{--}2.7{\%} improvement in EPR and a 17.4{--}20.6{\%} increase in EPR@16 compared to diverse baselines in three datasets. Further analyses reveal that iterative learning-to-rank effectively suppresses the arbitrariness of FOL representation by reducing the diversity of predicate signatures, and maintains strong performance across diverse inference types and out-of-domain data."
}