<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aly-vlachos-2024-tabver">
    <titleInfo>
        <title>TabVer: Tabular Fact Verification with Natural Logic</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rami</namePart>
        <namePart type="family">Aly</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andreas</namePart>
        <namePart type="family">Vlachos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Fact verification on tabular evidence incentivizes the use of symbolic reasoning models where a logical form is constructed (e.g., a LISP-style program), providing greater verifiability than fully neural approaches. However, these logical forms typically rely on well-formed tables, restricting their use in many scenarios. An emerging symbolic reasoning paradigm for textual evidence focuses on natural logic inference, which constructs proofs by modeling set-theoretic relations between a claim and its evidence in natural language. This approach provides flexibility and transparency but is less compatible with tabular evidence since the relations do not extend to arithmetic functions. We propose a set-theoretic interpretation of numerals and arithmetic functions in the context of natural logic, enabling the integration of arithmetic expressions in deterministic proofs. We leverage large language models to generate arithmetic expressions by generating questions about salient parts of a claim which are answered by executing appropriate functions on tables. In a few-shot setting on FEVEROUS, we achieve an accuracy of 71.4, outperforming both fully neural and symbolic reasoning models by 3.4 points. When evaluated on TabFact without any further training, our method remains competitive with an accuracy lead of 0.5 points.</abstract>
    <identifier type="citekey">aly-vlachos-2024-tabver</identifier>
    <identifier type="doi">10.1162/tacl_a_00722</identifier>
    <location>
        <url>https://aclanthology.org/2024.tacl-1.89/</url>
    </location>
    <part>
        <date>2024</date>
        <detail type="volume"><number>12</number></detail>
        <extent unit="page">
            <start>1648</start>
            <end>1671</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T TabVer: Tabular Fact Verification with Natural Logic
%A Aly, Rami
%A Vlachos, Andreas
%J Transactions of the Association for Computational Linguistics
%D 2024
%V 12
%I MIT Press
%C Cambridge, MA
%F aly-vlachos-2024-tabver
%X Fact verification on tabular evidence incentivizes the use of symbolic reasoning models where a logical form is constructed (e.g., a LISP-style program), providing greater verifiability than fully neural approaches. However, these logical forms typically rely on well-formed tables, restricting their use in many scenarios. An emerging symbolic reasoning paradigm for textual evidence focuses on natural logic inference, which constructs proofs by modeling set-theoretic relations between a claim and its evidence in natural language. This approach provides flexibility and transparency but is less compatible with tabular evidence since the relations do not extend to arithmetic functions. We propose a set-theoretic interpretation of numerals and arithmetic functions in the context of natural logic, enabling the integration of arithmetic expressions in deterministic proofs. We leverage large language models to generate arithmetic expressions by generating questions about salient parts of a claim which are answered by executing appropriate functions on tables. In a few-shot setting on FEVEROUS, we achieve an accuracy of 71.4, outperforming both fully neural and symbolic reasoning models by 3.4 points. When evaluated on TabFact without any further training, our method remains competitive with an accuracy lead of 0.5 points.
%R 10.1162/tacl_a_00722
%U https://aclanthology.org/2024.tacl-1.89/
%U https://doi.org/10.1162/tacl_a_00722
%P 1648-1671

Markdown (Informal)

[TabVer: Tabular Fact Verification with Natural Logic](https://aclanthology.org/2024.tacl-1.89/) (Aly & Vlachos, TACL 2024)

• TabVer: Tabular Fact Verification with Natural Logic (Aly & Vlachos, TACL 2024)

ACL

• Rami Aly and Andreas Vlachos. 2024. TabVer: Tabular Fact Verification with Natural Logic. Transactions of the Association for Computational Linguistics, 12:1648–1671.