@inproceedings{grover-etal-2024-navigating,
title = "Navigating Hallucinations for Reasoning of Unintentional Activities",
author = "Grover, Shresth and
Vineet, Vibhav and
Rawat, Yogesh",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.565",
pages = "9666--9680",
abstract = "In this work we present a novel task of understanding unintentional human activities in videos. We formalize this problem as a reasoning task under zero-shot scenario, where given a video of an unintentional activity we want to know why it transitioned from intentional to unintentional. We first evaluate the effectiveness of current state-of-the-art Large Multimodal Models on this reasoning task and observe that they suffer from hallucination. We further propose a novel prompting technique, termed as Dream of Thoughts (DoT), which allows the model to navigate through hallucinated thoughts to achieve better reasoning. To evaluate the performance on this task, we also introduce three different specialized metrics designed to quantify the models reasoning capability. We perform our experiments on three datasets, OOPs, UCF-Crimes, and ReUAct, and our findings show that DOT prompting technique is able to outperform standard prompting, while minimizing hallucinations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grover-etal-2024-navigating">
<titleInfo>
<title>Navigating Hallucinations for Reasoning of Unintentional Activities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shresth</namePart>
<namePart type="family">Grover</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vibhav</namePart>
<namePart type="family">Vineet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yogesh</namePart>
<namePart type="family">Rawat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work we present a novel task of understanding unintentional human activities in videos. We formalize this problem as a reasoning task under zero-shot scenario, where given a video of an unintentional activity we want to know why it transitioned from intentional to unintentional. We first evaluate the effectiveness of current state-of-the-art Large Multimodal Models on this reasoning task and observe that they suffer from hallucination. We further propose a novel prompting technique, termed as Dream of Thoughts (DoT), which allows the model to navigate through hallucinated thoughts to achieve better reasoning. To evaluate the performance on this task, we also introduce three different specialized metrics designed to quantify the models reasoning capability. We perform our experiments on three datasets, OOPs, UCF-Crimes, and ReUAct, and our findings show that DOT prompting technique is able to outperform standard prompting, while minimizing hallucinations.</abstract>
<identifier type="citekey">grover-etal-2024-navigating</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.565</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>9666</start>
<end>9680</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Navigating Hallucinations for Reasoning of Unintentional Activities
%A Grover, Shresth
%A Vineet, Vibhav
%A Rawat, Yogesh
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F grover-etal-2024-navigating
%X In this work we present a novel task of understanding unintentional human activities in videos. We formalize this problem as a reasoning task under zero-shot scenario, where given a video of an unintentional activity we want to know why it transitioned from intentional to unintentional. We first evaluate the effectiveness of current state-of-the-art Large Multimodal Models on this reasoning task and observe that they suffer from hallucination. We further propose a novel prompting technique, termed as Dream of Thoughts (DoT), which allows the model to navigate through hallucinated thoughts to achieve better reasoning. To evaluate the performance on this task, we also introduce three different specialized metrics designed to quantify the models reasoning capability. We perform our experiments on three datasets, OOPs, UCF-Crimes, and ReUAct, and our findings show that DOT prompting technique is able to outperform standard prompting, while minimizing hallucinations.
%U https://aclanthology.org/2024.findings-emnlp.565
%P 9666-9680
Markdown (Informal)
[Navigating Hallucinations for Reasoning of Unintentional Activities](https://aclanthology.org/2024.findings-emnlp.565) (Grover et al., Findings 2024)
ACL