@inproceedings{just-etal-2025-dipt,
title = "{D}i{PT}: Enhancing {LLM} Reasoning through Diversified Perspective-Taking",
author = "Just, Hoang Anh and
Dabas, Mahavir and
Huang, Lifu and
Jin, Ming and
Jia, Ruoxi",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.356/",
doi = "10.18653/v1/2025.findings-naacl.356",
pages = "6344--6374",
ISBN = "979-8-89176-195-7",
abstract = "Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors. Inspired by perspective-taking in social studies, this paper introduces DiPT, a novel approach that complements current reasoning methods by explicitly incorporating diversified viewpoints. This approach allows the model to gain a deeper understanding of the problem{'}s context and identify the most effective solution path during the inference stage. Additionally, it provides a general data-centric AI recipe for augmenting existing data to improve their quality for fine-tuning. Our empirical results demonstrate that DiPT can be flexibly integrated into existing methods that focus on a single reasoning approach, enhancing their reasoning performance and stability when presented with paraphrased problems. Furthermore, we illustrate improved context understanding by maintaining the model{'}s safe outputs against ``jailbreaking'' prompts intentionally designed to bypass safeguards built into deployed models. Lastly, we show that fine-tuning with data enriched with diverse perspectives can boost the reasoning capabilities of the model compared to fine-tuning with raw data alone."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="just-etal-2025-dipt">
<titleInfo>
<title>DiPT: Enhancing LLM Reasoning through Diversified Perspective-Taking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hoang</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Just</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahavir</namePart>
<namePart type="family">Dabas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruoxi</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors. Inspired by perspective-taking in social studies, this paper introduces DiPT, a novel approach that complements current reasoning methods by explicitly incorporating diversified viewpoints. This approach allows the model to gain a deeper understanding of the problem’s context and identify the most effective solution path during the inference stage. Additionally, it provides a general data-centric AI recipe for augmenting existing data to improve their quality for fine-tuning. Our empirical results demonstrate that DiPT can be flexibly integrated into existing methods that focus on a single reasoning approach, enhancing their reasoning performance and stability when presented with paraphrased problems. Furthermore, we illustrate improved context understanding by maintaining the model’s safe outputs against “jailbreaking” prompts intentionally designed to bypass safeguards built into deployed models. Lastly, we show that fine-tuning with data enriched with diverse perspectives can boost the reasoning capabilities of the model compared to fine-tuning with raw data alone.</abstract>
<identifier type="citekey">just-etal-2025-dipt</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.356</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.356/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6344</start>
<end>6374</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiPT: Enhancing LLM Reasoning through Diversified Perspective-Taking
%A Just, Hoang Anh
%A Dabas, Mahavir
%A Huang, Lifu
%A Jin, Ming
%A Jia, Ruoxi
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F just-etal-2025-dipt
%X Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors. Inspired by perspective-taking in social studies, this paper introduces DiPT, a novel approach that complements current reasoning methods by explicitly incorporating diversified viewpoints. This approach allows the model to gain a deeper understanding of the problem’s context and identify the most effective solution path during the inference stage. Additionally, it provides a general data-centric AI recipe for augmenting existing data to improve their quality for fine-tuning. Our empirical results demonstrate that DiPT can be flexibly integrated into existing methods that focus on a single reasoning approach, enhancing their reasoning performance and stability when presented with paraphrased problems. Furthermore, we illustrate improved context understanding by maintaining the model’s safe outputs against “jailbreaking” prompts intentionally designed to bypass safeguards built into deployed models. Lastly, we show that fine-tuning with data enriched with diverse perspectives can boost the reasoning capabilities of the model compared to fine-tuning with raw data alone.
%R 10.18653/v1/2025.findings-naacl.356
%U https://aclanthology.org/2025.findings-naacl.356/
%U https://doi.org/10.18653/v1/2025.findings-naacl.356
%P 6344-6374
Markdown (Informal)
[DiPT: Enhancing LLM Reasoning through Diversified Perspective-Taking](https://aclanthology.org/2025.findings-naacl.356/) (Just et al., Findings 2025)
ACL