Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies
AI design characteristics and human personality traits each impact the quality and outcomes of human-AI interactions. However, their relative and joint impacts are underexplored in imperfectly cooperative scenarios, where people and AI only have partially aligned goals and objectives. This study compares a purely simulated dataset comprising 2,000 simulations and a parallel human subjects experiment involving 290 human participants to investigate these effects across two scenario categories: (1) hiring negotiations between human job candidates and AI hiring agents; and (2) human-AI transactions wherein AI agents may conceal information to maximize internal goals. We examine user Extraversion and Agreeableness alongside AI design characteristics, including Adaptability, Expertise, and chain-of-thought Transparency. Our causal discovery analysis extends performance-focused evaluations by integrating scenario-based outcomes, communication analysis, and questionnaire measures. Results reveal divergences between purely simulated and human study datasets, and between scenario types. In simulation experiments, personality traits and AI attributes were comparatively influential. Yet, with actual human subjects, AI attributes -- particularly transparency -- were much more impactful. We discuss how these divergences vary across different interaction contexts, offering crucial insights for the future of human-centered AI agents.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Overcoming the Machine Penalty with Imperfectly Fair AI Agents
Despite rapid technological progress, effective human-machine cooperation remains a significant challenge. Humans tend to cooperate less with machines than with fellow humans, a phenomenon known as the machine penalty. H…
Modelling the Recommender Alignment Problem
Recommender systems (RS) mediate human experience online. Most RS act to optimize metrics that are imperfectly aligned with the best-interest of users but are easy to measure, like ad-clicks and user engagement. This has…
Recommendation SystemsInfluence of Early through Late Fusion on Pancreas Segmentation from Imperfectly Registered Multimodal MRI
Multimodal fusion promises better pancreas segmentation. However, where to perform fusion in models is still an open question. It is unclear if there is a best location to fuse information when analyzing pairs of imperfe…
Image RegistrationPancreas SegmentationSegmentationCooperative and Interaction-aware Driver Model for Lane Change Maneuver
To achieve complete autonomous vehicles, it is crucial for autonomous vehicles to communicate and interact with their surrounding vehicles. Especially, since the lane change scenarios do not have traffic signals and traf…
Autonomous VehiclesDecision MakingThe structure of multiplex networks predicts play in economic games and real-world cooperation
Explaining why humans cooperate in anonymous contexts is a major goal of human behavioral ecology, cultural evolution, and related fields. What predicts cooperation in anonymous contexts is inconsistent across population…
Sociology