<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2023-hallucination">
    <titleInfo>
        <title>Hallucination Detection for Grounded Instruction Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lingjun</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Khanh</namePart>
        <namePart type="family">Nguyen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hal</namePart>
        <namePart type="family">Daumé III</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We investigate the problem of generating instructions to guide humans to navigate in simulated residential environments. A major issue with current models is hallucination: they generate references to actions or objects that are inconsistent with what a human follower would perform or encounter along the described path. We develop a model that detects these hallucinated references by adopting a model pre-trained on a large corpus of image-text pairs, and fine-tuning it with a contrastive loss that separates correct instructions from instructions containing synthesized hallucinations. Our final model outperforms several baselines, including using word probability estimated by the instruction-generation model, and supervised models based on LSTM and Transformer.</abstract>
    <identifier type="citekey">zhao-etal-2023-hallucination</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.266</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.266</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>4044</start>
            <end>4053</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Hallucination Detection for Grounded Instruction Generation
%A Zhao, Lingjun
%A Nguyen, Khanh
%A Daumé III, Hal
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhao-etal-2023-hallucination
%X We investigate the problem of generating instructions to guide humans to navigate in simulated residential environments. A major issue with current models is hallucination: they generate references to actions or objects that are inconsistent with what a human follower would perform or encounter along the described path. We develop a model that detects these hallucinated references by adopting a model pre-trained on a large corpus of image-text pairs, and fine-tuning it with a contrastive loss that separates correct instructions from instructions containing synthesized hallucinations. Our final model outperforms several baselines, including using word probability estimated by the instruction-generation model, and supervised models based on LSTM and Transformer.
%R 10.18653/v1/2023.findings-emnlp.266
%U https://aclanthology.org/2023.findings-emnlp.266
%U https://doi.org/10.18653/v1/2023.findings-emnlp.266
%P 4044-4053

Markdown (Informal)

[Hallucination Detection for Grounded Instruction Generation](https://aclanthology.org/2023.findings-emnlp.266) (Zhao et al., Findings 2023)

• Hallucination Detection for Grounded Instruction Generation (Zhao et al., Findings 2023)

ACL

• Lingjun Zhao, Khanh Nguyen, and Hal Daumé III. 2023. Hallucination Detection for Grounded Instruction Generation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4044–4053, Singapore. Association for Computational Linguistics.