<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nafar-etal-2024-teaching">
    <titleInfo>
        <title>Teaching Probabilistic Logical Reasoning to Transformers</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Aliakbar</namePart>
        <namePart type="family">Nafar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">K</namePart>
        <namePart type="given">Brent</namePart>
        <namePart type="family">Venable</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Parisa</namePart>
        <namePart type="family">Kordjamshidi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yvette</namePart>
            <namePart type="family">Graham</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Purver</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we evaluate the capability of transformer-based language models in making inferences over uncertain text that includes uncertain rules of reasoning. We cover both Pre-trained Language Models (PLMs) and generative Large Language Models (LLMs). Our evaluation results show that both generations of language models struggle with reasoning over uncertain text. We propose a novel end-to-end fine-tuning approach, Probabilistic Constraint Training (PCT), that utilizes probabilistic logical rules as constraints in the fine-tuning phase without relying on these rules in the inference stage. To assess the effectiveness of PCT, we utilize the related corpora and, additionally, create a new and more challenging benchmark that, unlike the previous ones, uses instance-specific rules. Our study demonstrates that PCT improves the transformer-based language model’s intrinsic reasoning and makes their probabilistic logical reasoning process more explicit and explainable. Furthermore, PCT equips these models to effectively handle novel situations, including higher reasoning depth, new domains, and complex probabilistic structures.</abstract>
    <identifier type="citekey">nafar-etal-2024-teaching</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-eacl.112</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>1615</start>
            <end>1632</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Teaching Probabilistic Logical Reasoning to Transformers
%A Nafar, Aliakbar
%A Venable, K. Brent
%A Kordjamshidi, Parisa
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F nafar-etal-2024-teaching
%X In this paper, we evaluate the capability of transformer-based language models in making inferences over uncertain text that includes uncertain rules of reasoning. We cover both Pre-trained Language Models (PLMs) and generative Large Language Models (LLMs). Our evaluation results show that both generations of language models struggle with reasoning over uncertain text. We propose a novel end-to-end fine-tuning approach, Probabilistic Constraint Training (PCT), that utilizes probabilistic logical rules as constraints in the fine-tuning phase without relying on these rules in the inference stage. To assess the effectiveness of PCT, we utilize the related corpora and, additionally, create a new and more challenging benchmark that, unlike the previous ones, uses instance-specific rules. Our study demonstrates that PCT improves the transformer-based language model’s intrinsic reasoning and makes their probabilistic logical reasoning process more explicit and explainable. Furthermore, PCT equips these models to effectively handle novel situations, including higher reasoning depth, new domains, and complex probabilistic structures.
%U https://aclanthology.org/2024.findings-eacl.112
%P 1615-1632

Markdown (Informal)

[Teaching Probabilistic Logical Reasoning to Transformers](https://aclanthology.org/2024.findings-eacl.112) (Nafar et al., Findings 2024)

• Teaching Probabilistic Logical Reasoning to Transformers (Nafar et al., Findings 2024)

ACL

• Aliakbar Nafar, K. Brent Venable, and Parisa Kordjamshidi. 2024. Teaching Probabilistic Logical Reasoning to Transformers. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1615–1632, St. Julian’s, Malta. Association for Computational Linguistics.