@inproceedings{jung-etal-2024-perceptions,
title = "Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models",
author = "Jung, Chani and
Kim, Dongkwan and
Jin, Jiho and
Kim, Jiseon and
Seonwoo, Yeon and
Choi, Yejin and
Oh, Alice and
Kim, Hyunwoo",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1105",
doi = "10.18653/v1/2024.emnlp-main.1105",
pages = "19794--19809",
abstract = "While humans naturally develop theory of mind (ToM), the capability to understand other people{'}s mental states and beliefs, state-of-the-art large language models (LLMs) underperform on simple ToM benchmarks. We posit that we can extend our understanding of LLMs{'} ToM abilities by evaluating key human ToM precursors$-$perception inference and perception-to-belief inference$-$in LLMs. We introduce two datasets, Percept-ToMi and Percept-FANToM, to evaluate these precursory inferences for ToM in LLMs by annotating characters{'} perceptions on ToMi and FANToM, respectively.Our evaluation of eight state-of-the-art LLMs reveals that the models generally perform well in perception inference while exhibiting limited capability in perception-to-belief inference (e.g., lack of inhibitory control).Based on these results, we present PercepToM, a novel ToM method leveraging LLMs{'} strong perception inference capability while supplementing their limited perception-to-belief inference. Experimental results demonstrate that PercepToM significantly enhances LLM{'}s performance, especially in false belief scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jung-etal-2024-perceptions">
<titleInfo>
<title>Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chani</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongkwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiho</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiseon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeon</namePart>
<namePart type="family">Seonwoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunwoo</namePart>
<namePart type="family">Kim</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>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</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>While humans naturally develop theory of mind (ToM), the capability to understand other people’s mental states and beliefs, state-of-the-art large language models (LLMs) underperform on simple ToM benchmarks. We posit that we can extend our understanding of LLMs’ ToM abilities by evaluating key human ToM precursors-perception inference and perception-to-belief inference-in LLMs. We introduce two datasets, Percept-ToMi and Percept-FANToM, to evaluate these precursory inferences for ToM in LLMs by annotating characters’ perceptions on ToMi and FANToM, respectively.Our evaluation of eight state-of-the-art LLMs reveals that the models generally perform well in perception inference while exhibiting limited capability in perception-to-belief inference (e.g., lack of inhibitory control).Based on these results, we present PercepToM, a novel ToM method leveraging LLMs’ strong perception inference capability while supplementing their limited perception-to-belief inference. Experimental results demonstrate that PercepToM significantly enhances LLM’s performance, especially in false belief scenarios.</abstract>
<identifier type="citekey">jung-etal-2024-perceptions</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.1105</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.1105</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>19794</start>
<end>19809</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models
%A Jung, Chani
%A Kim, Dongkwan
%A Jin, Jiho
%A Kim, Jiseon
%A Seonwoo, Yeon
%A Choi, Yejin
%A Oh, Alice
%A Kim, Hyunwoo
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F jung-etal-2024-perceptions
%X While humans naturally develop theory of mind (ToM), the capability to understand other people’s mental states and beliefs, state-of-the-art large language models (LLMs) underperform on simple ToM benchmarks. We posit that we can extend our understanding of LLMs’ ToM abilities by evaluating key human ToM precursors-perception inference and perception-to-belief inference-in LLMs. We introduce two datasets, Percept-ToMi and Percept-FANToM, to evaluate these precursory inferences for ToM in LLMs by annotating characters’ perceptions on ToMi and FANToM, respectively.Our evaluation of eight state-of-the-art LLMs reveals that the models generally perform well in perception inference while exhibiting limited capability in perception-to-belief inference (e.g., lack of inhibitory control).Based on these results, we present PercepToM, a novel ToM method leveraging LLMs’ strong perception inference capability while supplementing their limited perception-to-belief inference. Experimental results demonstrate that PercepToM significantly enhances LLM’s performance, especially in false belief scenarios.
%R 10.18653/v1/2024.emnlp-main.1105
%U https://aclanthology.org/2024.emnlp-main.1105
%U https://doi.org/10.18653/v1/2024.emnlp-main.1105
%P 19794-19809
Markdown (Informal)
[Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models](https://aclanthology.org/2024.emnlp-main.1105) (Jung et al., EMNLP 2024)
ACL
- Chani Jung, Dongkwan Kim, Jiho Jin, Jiseon Kim, Yeon Seonwoo, Yejin Choi, Alice Oh, and Hyunwoo Kim. 2024. Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19794–19809, Miami, Florida, USA. Association for Computational Linguistics.