# Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations

arXiv: https://arxiv.org/abs/2410.13204 · HTML: https://mlsanity.com/paper/2410.13204/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 68 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions](https://mlsanity.com/paper/2308.11483/) (2023)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars](https://mlsanity.com/paper/2311.17227/) (2023)
- [LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models](https://mlsanity.com/paper/2404.01230/) (2024)
- [Strategic Reasoning with Language Models](https://mlsanity.com/paper/2305.19165/) (2023)
- [Escalation Risks from Language Models in Military and Diplomatic Decision-Making](https://mlsanity.com/paper/2401.03408/) (2024)
- [Are Large Language Models Consistent over Value-laden Questions?](https://mlsanity.com/paper/2407.02996/) (2024)
- [Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing](https://mlsanity.com/paper/2309.05898/) (2023)
- [Open Problems in Technical AI Governance](https://mlsanity.com/paper/2407.14981/) (2024)
- [MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization](https://mlsanity.com/paper/2301.12307/) (2023)
- [Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility](https://mlsanity.com/paper/2305.10235/) (2023)
- [Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation](https://mlsanity.com/paper/2406.11852/) (2024)
- [Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulations](https://mlsanity.com/paper/2403.03407/) (2024)
- [On Large Language Models in National Security Applications](https://mlsanity.com/paper/2407.03453/) (2024)
- [AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research](https://mlsanity.com/paper/2405.01859/) (2024)
- [Open-Ended Wargames with Large Language Models](https://mlsanity.com/paper/2404.11446/) (2024)
- [Evaluating Consistency and Reasoning Capabilities of Large Language Models](https://mlsanity.com/paper/2404.16478/) (2024)

## Built on by (most cited first, 11 of 11)

- [BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices](https://mlsanity.com/paper/2411.12990/) (2024)
- [Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents](https://mlsanity.com/paper/2505.02077/) (2025)
- [Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer](https://mlsanity.com/paper/2502.12964/) (2025)
- [Critical Foreign Policy Decisions (CFPD)-Benchmark: Measuring Diplomatic Preferences in Large Language Models](https://mlsanity.com/paper/2503.06263/) (2025)
- [HACK: Hallucinations Along Certainty and Knowledge Axes](https://mlsanity.com/paper/2510.24222/) (2025)
- [DICE: A Framework for Dimensional and Contextual Evaluation of Language Models](https://mlsanity.com/paper/2504.10359/) (2025)
- [Linearly Decoding Refused Knowledge in Aligned Language Models](https://mlsanity.com/paper/2507.00239/) (2025)
- [Shall We Play a Game? Language Models for Open-ended Wargames](https://mlsanity.com/paper/2509.17192/) (2025)
- [The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models](https://mlsanity.com/paper/2606.11082/) (2026)
- [Language models judge war differently when tested for alignment](https://mlsanity.com/paper/2609.05009/) (2026)
- [Position: AI Is Not Ready for Strategic Conflicts](https://mlsanity.com/paper/2609.16189/) (2026)

## Abstract (arXiv)

There is an increasing interest in using language models (LMs) for automated decision-making, with multiple countries actively testing LMs to aid in military crisis decision-making. To scrutinize relying on LM decision-making in high-stakes settings, we examine the inconsistency of responses in a crisis simulation ("wargame"), similar to reported tests conducted by the US military. Prior work illustrated escalatory tendencies and varying levels of aggression among LMs but were constrained to simulations with pre-defined actions. This was due to the challenges associated with quantitatively measuring semantic differences and evaluating natural language decision-making without relying on pre-defined actions. In this work, we query LMs for free form responses and use a metric based on BERTScore to measure response inconsistency quantitatively. Leveraging the benefits of BERTScore, we show that the inconsistency metric is robust to linguistic variations that preserve semantic meaning in a question-answering setting across text lengths. We show that all five tested LMs exhibit levels of inconsistency that indicate semantic differences, even when adjusting the wargame setting, anonymizing involved conflict countries, or adjusting the sampling temperature parameter T. Further qualitative evaluation shows that models recommend courses of action that share few to no similarities. We also study the impact of different prompt sensitivity variations on inconsistency at temperature T = 0. We find that inconsistency due to semantically equivalent prompt variations can exceed response inconsistency from temperature sampling for most studied models across different levels of ablations. Given the high-stakes nature of military deployment, we recommend further consideration be taken before using LMs to inform military decisions or other cases of high-stakes decision-making.