@inproceedings{peng-etal-2025-diplomacyagent,
title = "{D}iplomacy{A}gent: Do {LLM}s Balance Interests and Ethical Principles in International Events?",
author = "Peng, Jianxiang and
Shi, Ling and
Wu, Xinwei and
Zhang, Hanwen and
Liu, Fujiang and
Lyu, Haocheng and
Xiong, Deyi",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.693/",
doi = "10.18653/v1/2025.emnlp-main.693",
pages = "13732--13750",
ISBN = "979-8-89176-332-6",
abstract = "The widespread deployment of large language models (LLMs) across various domains has made their safety a critical priority. Inspired by think-tank decision-making philosophy, we propose DiplomacyAgent, an LLM-based multi-agent system for diplomatic position analysis. With DiplomacyAgent, we are able to systematically assess how LLMs balance ``interests'' against ``ethical principles'' when addressing various international events, hence understanding the safety implications of LLMs in diplomacy. Specifically, this will help to assess the consistency of LLM stance with widely recognized ethical standards, as well as the potential risks or ideological biases that may arise. Through integrated quantitative metrics, our research uncovers unexpected decision-making patterns in LLM responses to sensitive issues including human rights protection, environmental sustainability, regional conflicts, etc. It discloses that LLMs could exhibit a strong bias towards interests, leading to unsafe decisions that violate ethical and moral principles. Our experiment results suggest that deploying LLMs in high-stakes domains, particularly in the formulation of diplomatic policies, necessitates a comprehensive assessment of potential ethical and social implications, as well as the implementation of stringent safety protocols."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-etal-2025-diplomacyagent">
<titleInfo>
<title>DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianxiang</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ling</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinwei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanwen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fujiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haocheng</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>The widespread deployment of large language models (LLMs) across various domains has made their safety a critical priority. Inspired by think-tank decision-making philosophy, we propose DiplomacyAgent, an LLM-based multi-agent system for diplomatic position analysis. With DiplomacyAgent, we are able to systematically assess how LLMs balance “interests” against “ethical principles” when addressing various international events, hence understanding the safety implications of LLMs in diplomacy. Specifically, this will help to assess the consistency of LLM stance with widely recognized ethical standards, as well as the potential risks or ideological biases that may arise. Through integrated quantitative metrics, our research uncovers unexpected decision-making patterns in LLM responses to sensitive issues including human rights protection, environmental sustainability, regional conflicts, etc. It discloses that LLMs could exhibit a strong bias towards interests, leading to unsafe decisions that violate ethical and moral principles. Our experiment results suggest that deploying LLMs in high-stakes domains, particularly in the formulation of diplomatic policies, necessitates a comprehensive assessment of potential ethical and social implications, as well as the implementation of stringent safety protocols.</abstract>
<identifier type="citekey">peng-etal-2025-diplomacyagent</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.693</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.693/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>13732</start>
<end>13750</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events?
%A Peng, Jianxiang
%A Shi, Ling
%A Wu, Xinwei
%A Zhang, Hanwen
%A Liu, Fujiang
%A Lyu, Haocheng
%A Xiong, Deyi
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F peng-etal-2025-diplomacyagent
%X The widespread deployment of large language models (LLMs) across various domains has made their safety a critical priority. Inspired by think-tank decision-making philosophy, we propose DiplomacyAgent, an LLM-based multi-agent system for diplomatic position analysis. With DiplomacyAgent, we are able to systematically assess how LLMs balance “interests” against “ethical principles” when addressing various international events, hence understanding the safety implications of LLMs in diplomacy. Specifically, this will help to assess the consistency of LLM stance with widely recognized ethical standards, as well as the potential risks or ideological biases that may arise. Through integrated quantitative metrics, our research uncovers unexpected decision-making patterns in LLM responses to sensitive issues including human rights protection, environmental sustainability, regional conflicts, etc. It discloses that LLMs could exhibit a strong bias towards interests, leading to unsafe decisions that violate ethical and moral principles. Our experiment results suggest that deploying LLMs in high-stakes domains, particularly in the formulation of diplomatic policies, necessitates a comprehensive assessment of potential ethical and social implications, as well as the implementation of stringent safety protocols.
%R 10.18653/v1/2025.emnlp-main.693
%U https://aclanthology.org/2025.emnlp-main.693/
%U https://doi.org/10.18653/v1/2025.emnlp-main.693
%P 13732-13750
Markdown (Informal)
[DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events?](https://aclanthology.org/2025.emnlp-main.693/) (Peng et al., EMNLP 2025)
ACL