Model Cards for AI Teammates: Comparing Human-AI Team Familiarization Methods for High-Stakes Environments

2025-05-19

AI Summary

This study addresses the challenge of optimizing human-AI team effectiveness in high-risk, collaborative intelligence, surveillance, and reconnaissance (ISR) missions. We empirically compared three AI teammate familiarization methods—document-based instruction, joint training, and no familiarization—assessing their impact on human operators’ strategy formation, risk preference, and control behavior. A controlled user study with 60 participants integrated behavioral metrics, semi-structured interviews, and human factors evaluations. Results show that document-based familiarization accelerates strategy adoption but induces excessive risk aversion; interactive joint training enhances risk tolerance and exploratory behavior; and a hybrid framework—integrating guided documentation, structured hands-on practice, and unstructured interaction—achieves superior balance between team performance and decision interpretability. This work presents the first multidimensional empirical evaluation of AI familiarization pathways in high-stakes operational contexts and proposes a generalizable, evidence-informed hybrid familiarization design paradigm.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: Human-Robot Interaction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

We compare three methods of familiarizing a human with an artificial intelligence (AI) teammate ("agent") prior to operation in a collaborative, fast-paced intelligence, surveillance, and reconnaissance (ISR) environment. In a between-subjects user study (n=60), participants either read documentation about the agent, trained alongside the agent prior to the mission, or were given no familiarization. Results showed that the most valuable information about the agent included details of its decision-making algorithms and its relative strengths and weaknesses compared to the human. This information allowed the familiarization groups to form sophisticated team strategies more quickly than the control group. Documentation-based familiarization led to the fastest adoption of these strategies, but also biased participants towards risk-averse behavior that prevented high scores. Participants familiarized through direct interaction were able to infer much of the same information through observation, and were more willing to take risks and experiment with different control modes, but reported weaker understanding of the agent's internal processes. Significant differences were seen between individual participants' risk tolerance and methods of AI interaction, which should be considered when designing human-AI control interfaces. Based on our findings, we recommend a human-AI team familiarization method that combines AI documentation, structured in-situ training, and exploratory interaction.

Problem

• Comparing human-AI team familiarization methods for high-stakes ISR environments
• Evaluating impact of agent documentation versus interactive training on strategy formation
• Assessing risk tolerance differences in human-AI interaction methods

Innovation

• Compare three human-AI team familiarization methods
• Documentation reveals AI decision-making and strengths
• Combine documentation, training, and exploratory interaction