<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-lim-2024-language">
    <titleInfo>
        <title>Language Models Don’t Learn the Physical Manifestation of Language</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bruce</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaehyuk</namePart>
        <namePart type="family">Lim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We argue that language-only models don’t learn the physical manifestation of language. We present an empirical investigation of visual-auditory properties of language through a series of tasks, termed H-Test.These tasks highlight a fundamental gap between human linguistic understanding and the sensory-deprived linguistic understanding of LLMs. In support of our hypothesis, 1. deliberate reasoning (Chain-of-Thought), 2. few-shot examples, or 3. stronger LLM from the same model family (LLaMA 2 13B -\textgreater LLaMA 2 70B) has no significant effect on H-Test performance. We bring in the philosophical case of Mary, who learns about the world in a sensory-deprived environment as a useful conceptual framework to understand how language-only models learn about the world (Jackson, 1986). Our experiments show that some of the strongest proprietary LLMs stay near random chance baseline accuracy of 50%, highlighting the limitations of linguistic knowledge acquired in the absence of sensory experience. Our code and data are available at \textlessgithub.com/brucewlee/h-test\textgreater.</abstract>
    <identifier type="citekey">lee-lim-2024-language</identifier>
    <location>
        <url>https://aclanthology.org/2024.acl-long.195</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>3554</start>
            <end>3579</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Language Models Don’t Learn the Physical Manifestation of Language
%A Lee, Bruce
%A Lim, Jaehyuk
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F lee-lim-2024-language
%X We argue that language-only models don’t learn the physical manifestation of language. We present an empirical investigation of visual-auditory properties of language through a series of tasks, termed H-Test.These tasks highlight a fundamental gap between human linguistic understanding and the sensory-deprived linguistic understanding of LLMs. In support of our hypothesis, 1. deliberate reasoning (Chain-of-Thought), 2. few-shot examples, or 3. stronger LLM from the same model family (LLaMA 2 13B -\textgreater LLaMA 2 70B) has no significant effect on H-Test performance. We bring in the philosophical case of Mary, who learns about the world in a sensory-deprived environment as a useful conceptual framework to understand how language-only models learn about the world (Jackson, 1986). Our experiments show that some of the strongest proprietary LLMs stay near random chance baseline accuracy of 50%, highlighting the limitations of linguistic knowledge acquired in the absence of sensory experience. Our code and data are available at \textlessgithub.com/brucewlee/h-test\textgreater.
%U https://aclanthology.org/2024.acl-long.195
%P 3554-3579

Markdown (Informal)

[Language Models Don’t Learn the Physical Manifestation of Language](https://aclanthology.org/2024.acl-long.195) (Lee & Lim, ACL 2024)

• Language Models Don’t Learn the Physical Manifestation of Language (Lee & Lim, ACL 2024)

ACL

• Bruce Lee and Jaehyuk Lim. 2024. Language Models Don’t Learn the Physical Manifestation of Language. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3554–3579, Bangkok, Thailand. Association for Computational Linguistics.