@inproceedings{wilf-etal-2024-think,
title = "Think Twice: Perspective-Taking Improves Large Language Models{'} Theory-of-Mind Capabilities",
author = "Wilf, Alex and
Lee, Sihyun and
Liang, Paul Pu and
Morency, Louis-Philippe",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.451",
pages = "8292--8308",
abstract = "Human interactions are deeply rooted in the interplay of thoughts, beliefs, and desires made possible by Theory of Mind (ToM): our cognitive ability to understand the mental states of ourselves and others. Although ToM may come naturally to us, emulating it presents a challenge to even the most advanced Large Language Models (LLMs). Recent improvements to LLMs{'} reasoning capabilities from simple yet effective prompting techniques such as Chain-of-Thought (CoT) have seen limited applicability to ToM. In this paper, we turn to the prominent cognitive science theory {``}Simulation Theory{''} to bridge this gap. We introduce SimToM, a novel two-stage prompting framework inspired by Simulation Theory{'}s notion of perspective-taking. To implement this idea on current ToM benchmarks, SimToM first filters context based on what the character in question knows before answering a question about their mental state. Our approach, which requires no additional training and minimal prompt-tuning, shows substantial improvement over existing methods, and our analysis reveals the importance of perspective-taking to Theory-of-Mind capabilities. Our findings suggest perspective-taking as a promising direction for future research into improving LLMs{'} ToM capabilities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wilf-etal-2024-think">
<titleInfo>
<title>Think Twice: Perspective-Taking Improves Large Language Models’ Theory-of-Mind Capabilities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Wilf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sihyun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="given">Pu</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis-Philippe</namePart>
<namePart type="family">Morency</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>Human interactions are deeply rooted in the interplay of thoughts, beliefs, and desires made possible by Theory of Mind (ToM): our cognitive ability to understand the mental states of ourselves and others. Although ToM may come naturally to us, emulating it presents a challenge to even the most advanced Large Language Models (LLMs). Recent improvements to LLMs’ reasoning capabilities from simple yet effective prompting techniques such as Chain-of-Thought (CoT) have seen limited applicability to ToM. In this paper, we turn to the prominent cognitive science theory “Simulation Theory” to bridge this gap. We introduce SimToM, a novel two-stage prompting framework inspired by Simulation Theory’s notion of perspective-taking. To implement this idea on current ToM benchmarks, SimToM first filters context based on what the character in question knows before answering a question about their mental state. Our approach, which requires no additional training and minimal prompt-tuning, shows substantial improvement over existing methods, and our analysis reveals the importance of perspective-taking to Theory-of-Mind capabilities. Our findings suggest perspective-taking as a promising direction for future research into improving LLMs’ ToM capabilities.</abstract>
<identifier type="citekey">wilf-etal-2024-think</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.451</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>8292</start>
<end>8308</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Think Twice: Perspective-Taking Improves Large Language Models’ Theory-of-Mind Capabilities
%A Wilf, Alex
%A Lee, Sihyun
%A Liang, Paul Pu
%A Morency, Louis-Philippe
%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 wilf-etal-2024-think
%X Human interactions are deeply rooted in the interplay of thoughts, beliefs, and desires made possible by Theory of Mind (ToM): our cognitive ability to understand the mental states of ourselves and others. Although ToM may come naturally to us, emulating it presents a challenge to even the most advanced Large Language Models (LLMs). Recent improvements to LLMs’ reasoning capabilities from simple yet effective prompting techniques such as Chain-of-Thought (CoT) have seen limited applicability to ToM. In this paper, we turn to the prominent cognitive science theory “Simulation Theory” to bridge this gap. We introduce SimToM, a novel two-stage prompting framework inspired by Simulation Theory’s notion of perspective-taking. To implement this idea on current ToM benchmarks, SimToM first filters context based on what the character in question knows before answering a question about their mental state. Our approach, which requires no additional training and minimal prompt-tuning, shows substantial improvement over existing methods, and our analysis reveals the importance of perspective-taking to Theory-of-Mind capabilities. Our findings suggest perspective-taking as a promising direction for future research into improving LLMs’ ToM capabilities.
%U https://aclanthology.org/2024.acl-long.451
%P 8292-8308
Markdown (Informal)
[Think Twice: Perspective-Taking Improves Large Language Models’ Theory-of-Mind Capabilities](https://aclanthology.org/2024.acl-long.451) (Wilf et al., ACL 2024)
ACL