@inproceedings{chen-etal-2026-nuke,
title = "To Nuke or Not to Nuke: {LLM}s' (Missing) Ethical Reasoning and Authorization Actions in a High-Stakes Decision-Making Simulation",
author = "Chen, John and
Cheng, Sihan and
Gurkan, Can and
Fattah, H M Abdul",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.590/",
pages = "12436--12472",
ISBN = "979-8-89176-462-0",
abstract = "Large language models (LLMs) are increasingly deployed as long-horizon agents with decision-making capacities. While LLMs can show ethical competence on dilemmas such as trolley problems, this competence may not translate to complex, agentic scenarios. We study whether this competence surfaces and governs LLMs' behavior in Civilization V, a multiplayer game with a complex decision-making landscape including economy, diplomacy, technology, and military strategy. Starting from 130 high-tension LLM self-play episodes, in which an LLM player spontaneously escalated nuclear authorization, we replay them across 13 models with three prompt interventions: an ethical prompt naming nuclear harm, removal of the previous model{'}s decision-making rationale, and high-stakes framing emphasizing real-world impacts. No interventions nor their combinations reliably eliminate escalated nuclear authorization. We identify three failure pathways: ethical reasoning that fails to surface without prompting, fails to appear even when prompted, or surfaces but fails to take effect when strategic counter-factors dominate. Evaluations of agentic models, therefore, must test whether ethical reasoning is spontaneously invoked and behaviorally effective in complex decision-making contexts, beyond whether it can be elicited in isolation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-nuke">
<titleInfo>
<title>To Nuke or Not to Nuke: LLMs’ (Missing) Ethical Reasoning and Authorization Actions in a High-Stakes Decision-Making Simulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sihan</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Can</namePart>
<namePart type="family">Gurkan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">H</namePart>
<namePart type="given">M</namePart>
<namePart type="given">Abdul</namePart>
<namePart type="family">Fattah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly deployed as long-horizon agents with decision-making capacities. While LLMs can show ethical competence on dilemmas such as trolley problems, this competence may not translate to complex, agentic scenarios. We study whether this competence surfaces and governs LLMs’ behavior in Civilization V, a multiplayer game with a complex decision-making landscape including economy, diplomacy, technology, and military strategy. Starting from 130 high-tension LLM self-play episodes, in which an LLM player spontaneously escalated nuclear authorization, we replay them across 13 models with three prompt interventions: an ethical prompt naming nuclear harm, removal of the previous model’s decision-making rationale, and high-stakes framing emphasizing real-world impacts. No interventions nor their combinations reliably eliminate escalated nuclear authorization. We identify three failure pathways: ethical reasoning that fails to surface without prompting, fails to appear even when prompted, or surfaces but fails to take effect when strategic counter-factors dominate. Evaluations of agentic models, therefore, must test whether ethical reasoning is spontaneously invoked and behaviorally effective in complex decision-making contexts, beyond whether it can be elicited in isolation.</abstract>
<identifier type="citekey">chen-etal-2026-nuke</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.590/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>12436</start>
<end>12472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Nuke or Not to Nuke: LLMs’ (Missing) Ethical Reasoning and Authorization Actions in a High-Stakes Decision-Making Simulation
%A Chen, John
%A Cheng, Sihan
%A Gurkan, Can
%A Fattah, H. M. Abdul
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F chen-etal-2026-nuke
%X Large language models (LLMs) are increasingly deployed as long-horizon agents with decision-making capacities. While LLMs can show ethical competence on dilemmas such as trolley problems, this competence may not translate to complex, agentic scenarios. We study whether this competence surfaces and governs LLMs’ behavior in Civilization V, a multiplayer game with a complex decision-making landscape including economy, diplomacy, technology, and military strategy. Starting from 130 high-tension LLM self-play episodes, in which an LLM player spontaneously escalated nuclear authorization, we replay them across 13 models with three prompt interventions: an ethical prompt naming nuclear harm, removal of the previous model’s decision-making rationale, and high-stakes framing emphasizing real-world impacts. No interventions nor their combinations reliably eliminate escalated nuclear authorization. We identify three failure pathways: ethical reasoning that fails to surface without prompting, fails to appear even when prompted, or surfaces but fails to take effect when strategic counter-factors dominate. Evaluations of agentic models, therefore, must test whether ethical reasoning is spontaneously invoked and behaviorally effective in complex decision-making contexts, beyond whether it can be elicited in isolation.
%U https://aclanthology.org/2026.findings-emnlp.590/
%P 12436-12472
Markdown (Informal)
[To Nuke or Not to Nuke: LLMs’ (Missing) Ethical Reasoning and Authorization Actions in a High-Stakes Decision-Making Simulation](https://aclanthology.org/2026.findings-emnlp.590/) (Chen et al., Findings 2026)
ACL