Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation

Jihao Shi; Xiao Ding; Kai Xiong; Hengwei Zhao; Bing Qin (秦兵); Ting Liu (刘挺)

doi:10.18653/v1/2025.findings-acl.893

Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation

Jihao Shi, Xiao Ding, Kai Xiong, Hengwei Zhao, Bing Qin, Ting Liu

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Entailment trees are essential for enhancing interpretability and transparency in tasks like question answering and natural language understanding. However, existing approaches often lack logical consistency, as they rely on static reward structures or ignore the intricate dependencies within multi-step reasoning. To address these limitations, we propose a method that integrates natural logic principles into reinforcement learning, enabling dynamic reward computation to guide entailment tree generation. Our approach ensures logical consistency across reasoning steps while improving interpretability and generalization. Experiments on EntailmentBank demonstrate significant improvements over state-of-the-art methods, highlighting the effectiveness of natural logic in structured reasoning.

Anthology ID:: 2025.findings-acl.893
Volume:: Findings of the Association for Computational Linguistics: ACL 2025
Month:: July
Year:: 2025
Address:: Vienna, Austria
Editors:: Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 17372–17382
Language:
URL:: https://aclanthology.org/2025.findings-acl.893/
DOI:: 10.18653/v1/2025.findings-acl.893
Bibkey:
Cite (ACL):: Jihao Shi, Xiao Ding, Kai Xiong, Hengwei Zhao, Bing Qin, and Ting Liu. 2025. Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 17372–17382, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation (Shi et al., Findings 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.findings-acl.893.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{shi-etal-2025-natural,
    title = "Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation",
    author = "Shi, Jihao  and
      Ding, Xiao  and
      Xiong, Kai  and
      Zhao, Hengwei  and
      Qin, Bing  and
      Liu, Ting",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-acl.893/",
    doi = "10.18653/v1/2025.findings-acl.893",
    pages = "17372--17382",
    ISBN = "979-8-89176-256-5",
    abstract = "Entailment trees are essential for enhancing interpretability and transparency in tasks like question answering and natural language understanding. However, existing approaches often lack logical consistency, as they rely on static reward structures or ignore the intricate dependencies within multi-step reasoning. To address these limitations, we propose a method that integrates natural logic principles into reinforcement learning, enabling dynamic reward computation to guide entailment tree generation. Our approach ensures logical consistency across reasoning steps while improving interpretability and generalization. Experiments on EntailmentBank demonstrate significant improvements over state-of-the-art methods, highlighting the effectiveness of natural logic in structured reasoning."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2025-natural">
    <titleInfo>
        <title>Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jihao</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiao</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kai</namePart>
        <namePart type="family">Xiong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hengwei</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bing</namePart>
        <namePart type="family">Qin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ting</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Entailment trees are essential for enhancing interpretability and transparency in tasks like question answering and natural language understanding. However, existing approaches often lack logical consistency, as they rely on static reward structures or ignore the intricate dependencies within multi-step reasoning. To address these limitations, we propose a method that integrates natural logic principles into reinforcement learning, enabling dynamic reward computation to guide entailment tree generation. Our approach ensures logical consistency across reasoning steps while improving interpretability and generalization. Experiments on EntailmentBank demonstrate significant improvements over state-of-the-art methods, highlighting the effectiveness of natural logic in structured reasoning.</abstract>
    <identifier type="citekey">shi-etal-2025-natural</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.893</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.893/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>17372</start>
            <end>17382</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation
%A Shi, Jihao
%A Ding, Xiao
%A Xiong, Kai
%A Zhao, Hengwei
%A Qin, Bing
%A Liu, Ting
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F shi-etal-2025-natural
%X Entailment trees are essential for enhancing interpretability and transparency in tasks like question answering and natural language understanding. However, existing approaches often lack logical consistency, as they rely on static reward structures or ignore the intricate dependencies within multi-step reasoning. To address these limitations, we propose a method that integrates natural logic principles into reinforcement learning, enabling dynamic reward computation to guide entailment tree generation. Our approach ensures logical consistency across reasoning steps while improving interpretability and generalization. Experiments on EntailmentBank demonstrate significant improvements over state-of-the-art methods, highlighting the effectiveness of natural logic in structured reasoning.
%R 10.18653/v1/2025.findings-acl.893
%U https://aclanthology.org/2025.findings-acl.893/
%U https://doi.org/10.18653/v1/2025.findings-acl.893
%P 17372-17382

Download as File

Markdown (Informal)

[Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation](https://aclanthology.org/2025.findings-acl.893/) (Shi et al., Findings 2025)

Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation (Shi et al., Findings 2025)

ACL

Jihao Shi, Xiao Ding, Kai Xiong, Hengwei Zhao, Bing Qin, and Ting Liu. 2025. Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 17372–17382, Vienna, Austria. Association for Computational Linguistics.