<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhar-asher-2024-strong">
    <titleInfo>
        <title>Strong hallucinations from negation and how to fix them</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Swarnadeep</namePart>
        <namePart type="family">Bhar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicholas</namePart>
        <namePart type="family">Asher</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>Findings of the Association for Computational Linguistics ACL 2024</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 and virtual meeting</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Despite great performance on many tasks, language models (LMs) still struggle with reasoning, sometimes providing responses that cannot possibly be true because they stem from logical incoherence. We call such responses strong hallucinations and prove that they follow from an LM’s computation of its internal representations for logical operators and outputs from those representations. Focusing on negation, we provide a novel solution in which negation is treated not as another element of a latent representation, but as an operation over an LM’s latent representations that constrains how they may evolve. We show that our approach improves model performance in cloze prompting and natural language inference tasks with negation without requiring training on sparse negative data.</abstract>
    <identifier type="citekey">bhar-asher-2024-strong</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.752</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>12670</start>
            <end>12687</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Strong hallucinations from negation and how to fix them
%A Bhar, Swarnadeep
%A Asher, Nicholas
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F bhar-asher-2024-strong
%X Despite great performance on many tasks, language models (LMs) still struggle with reasoning, sometimes providing responses that cannot possibly be true because they stem from logical incoherence. We call such responses strong hallucinations and prove that they follow from an LM’s computation of its internal representations for logical operators and outputs from those representations. Focusing on negation, we provide a novel solution in which negation is treated not as another element of a latent representation, but as an operation over an LM’s latent representations that constrains how they may evolve. We show that our approach improves model performance in cloze prompting and natural language inference tasks with negation without requiring training on sparse negative data.
%U https://aclanthology.org/2024.findings-acl.752
%P 12670-12687

Markdown (Informal)

[Strong hallucinations from negation and how to fix them](https://aclanthology.org/2024.findings-acl.752) (Bhar & Asher, Findings 2024)

• Strong hallucinations from negation and how to fix them (Bhar & Asher, Findings 2024)

ACL

• Swarnadeep Bhar and Nicholas Asher. 2024. Strong hallucinations from negation and how to fix them. In Findings of the Association for Computational Linguistics ACL 2024, pages 12670–12687, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.