Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulations
- URL: http://arxiv.org/abs/2403.03407v2
- Date: Mon, 3 Jun 2024 15:00:47 GMT
- Title: Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulations
- Authors: Max Lamparth, Anthony Corso, Jacob Ganz, Oriana Skylar Mastro, Jacquelyn Schneider, Harold Trinkunas,
- Abstract summary: We show that large language models (LLMs) behave differently compared to humans in high-stakes military decision-making scenarios.
Our results motivate policymakers to be cautious before granting autonomy or following AI-based strategy recommendations.
- Score: 1.6108153271585284
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: To some, the advent of artificial intelligence (AI) promises better decision-making and increased military effectiveness while reducing the influence of human error and emotions. However, there is still debate about how AI systems, especially large language models (LLMs), behave compared to humans in high-stakes military decision-making scenarios with the potential for increased risks towards escalation and unnecessary conflicts. To test this potential and scrutinize the use of LLMs for such purposes, we use a new wargame experiment with 107 national security experts designed to look at crisis escalation in a fictional US-China scenario and compare human players to LLM-simulated responses in separate simulations. Wargames have a long history in the development of military strategy and the response of nations to threats or attacks. Here, we show a considerable high-level agreement in the LLM and human responses and significant quantitative and qualitative differences in individual actions and strategic tendencies. These differences depend on intrinsic biases in LLMs regarding the appropriate level of violence following strategic instructions, the choice of LLM, and whether the LLMs are tasked to decide for a team of players directly or first to simulate dialog between players. When simulating the dialog, the discussions lack quality and maintain a farcical harmony. The LLM simulations cannot account for human player characteristics, showing no significant difference even for extreme traits, such as "pacifist" or "aggressive sociopath". Our results motivate policymakers to be cautious before granting autonomy or following AI-based strategy recommendations.
Related papers
- Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma? [0.1474723404975345]
We study the cooperative behavior of Llama2 when playing the Iterated Prisoner's Dilemma against random adversaries displaying various levels of hostility.
We find that Llama2 tends not to initiate defection but it adopts a cautious approach towards cooperation.
In comparison to prior research on human participants, Llama2 exhibits a greater inclination towards cooperative behavior.
arXiv Detail & Related papers (2024-06-19T14:51:14Z) - Toward Human-AI Alignment in Large-Scale Multi-Player Games [24.784173202415687]
We analyze extensive human gameplay data from Xbox's Bleeding Edge (100K+ games)
We find that while human players exhibit variability in fight-flight and explore-exploit behavior, AI players tend towards uniformity.
These stark differences underscore the need for interpretable evaluation, design, and integration of AI in human-aligned applications.
arXiv Detail & Related papers (2024-02-05T22:55:33Z) - CivRealm: A Learning and Reasoning Odyssey in Civilization for
Decision-Making Agents [63.79739920174535]
We introduce CivRealm, an environment inspired by the Civilization game.
CivRealm stands as a unique learning and reasoning challenge for decision-making agents.
arXiv Detail & Related papers (2024-01-19T09:14:11Z) - Escalation Risks from Language Models in Military and Diplomatic
Decision-Making [0.0]
This work aims to scrutinize the behavior of multiple AI agents in simulated wargames.
We design a novel wargame simulation and scoring framework to assess the risks of the escalation of actions taken by these agents.
We observe that models tend to develop arms-race dynamics, leading to greater conflict, and in rare cases, even to the deployment of nuclear weapons.
arXiv Detail & Related papers (2024-01-07T07:59:10Z) - War and Peace (WarAgent): Large Language Model-based Multi-Agent
Simulation of World Wars [40.489161847202325]
We propose textbfWarAgent, an LLM-powered multi-agent AI system, to simulate historical international conflicts.
By evaluating the simulation effectiveness, we examine the advancements and limitations of cutting-edge AI systems' abilities.
Our findings offer data-driven and AI-augmented insights that can redefine how we approach conflict resolution and peacekeeping strategies.
arXiv Detail & Related papers (2023-11-28T20:59:49Z) - ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic
Decision-Making with AI Agents [77.34720446306419]
Alympics is a systematic simulation framework utilizing Large Language Model (LLM) agents for game theory research.
Alympics creates a versatile platform for studying complex game theory problems.
arXiv Detail & Related papers (2023-11-06T16:03:46Z) - Leveraging Word Guessing Games to Assess the Intelligence of Large
Language Models [105.39236338147715]
The paper is inspired by the popular language game Who is Spy''
We develop DEEP to evaluate LLMs' expression and disguising abilities.
We then introduce SpyGame, an interactive multi-agent framework.
arXiv Detail & Related papers (2023-10-31T14:37:42Z) - Language Agents with Reinforcement Learning for Strategic Play in the
Werewolf Game [40.438765131992525]
We develop strategic language agents that generate flexible language actions and possess strong decision-making abilities.
To mitigate the intrinsic bias in language actions, our agents use an LLM to perform deductive reasoning and generate a diverse set of action candidates.
Experiments show that our agents overcome the intrinsic bias and outperform existing LLM-based agents in the Werewolf game.
arXiv Detail & Related papers (2023-10-29T09:02:57Z) - Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation [52.930183136111864]
We propose using scorable negotiation to evaluate Large Language Models (LLMs)
To reach an agreement, agents must have strong arithmetic, inference, exploration, and planning capabilities.
We provide procedures to create new games and increase games' difficulty to have an evolving benchmark.
arXiv Detail & Related papers (2023-09-29T13:33:06Z) - When to Make Exceptions: Exploring Language Models as Accounts of Human
Moral Judgment [96.77970239683475]
AI systems need to be able to understand, interpret and predict human moral judgments and decisions.
A central challenge for AI safety is capturing the flexibility of the human moral mind.
We present a novel challenge set consisting of rule-breaking question answering.
arXiv Detail & Related papers (2022-10-04T09:04:27Z) - Modeling Strong and Human-Like Gameplay with KL-Regularized Search [64.24339197581769]
We consider the task of building strong but human-like policies in multi-agent decision-making problems.
Imitation learning is effective at predicting human actions but may not match the strength of expert humans.
We show in chess and Go that regularizing search policies based on the KL divergence from an imitation-learned policy by applying Monte Carlo tree search produces policies that have higher human prediction accuracy and are stronger than the imitation policy.
arXiv Detail & Related papers (2021-12-14T16:52:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.