Luisa Vervier

Philipp Brauner, Felix Glawe, Gian Luca Liehner et al.

Understanding public perception of artificial intelligence (AI) and the tradeoffs between potential risks and benefits is crucial, as these perceptions might shape policy decisions, influence innovation trajectories for successful market strategies, and determine individual and societal acceptance of AI technologies. Using a representative sample of 1100 participants from Germany, this study examines mental models of AI. Participants quantitatively evaluated 71 statements about AI's future capabilities (e.g., autonomous driving, medical care, art, politics, warfare, and societal divides), assessing the expected likelihood of occurrence, perceived risks, benefits, and overall value. We present rankings of these projections alongside visual mappings illustrating public risk-benefit tradeoffs. While many scenarios were deemed likely, participants often associated them with high risks, limited benefits, and low overall value. Across all scenarios, 96.4% ($r^2=96.4\%$) of the variance in value assessment can be explained by perceived risks ($β=-.504$) and perceived benefits ($β=+.710$), with no significant relation to expected likelihood. Demographics and personality traits influenced perceptions of risks, benefits, and overall evaluations, underscoring the importance of increasing AI literacy and tailoring public information to diverse user needs. These findings provide actionable insights for researchers, developers, and policymakers by highlighting critical public concerns and individual factors essential to align AI development with individual values.

Philipp Brauner, Felix Glawe, Gian Luca Liehner et al.

As artificial intelligence (AI) continues to advance, understanding public perceptions -- including biases, risks, and benefits -- is essential for guiding research priorities and AI alignment, shaping public discourse, and informing policy. This exploratory study investigates cultural differences in mental models of AI using 71 imaginaries of AI's potential futures. Drawing on cross-cultural convenience samples from Germany (N=52) and China (N=60), we identify significant differences in expectations, evaluations, and risk-benefit tradeoffs. Participants from Germany generally provided more cautious assessments, whereas participants from China expressed greater optimism regarding AI's societal benefits. Chinese participants exhibited relatively balanced risk-benefit tradeoffs ($β=-0.463$ for risk and $β=+0.484$ for benefit, $r^2=.630$). In contrast, German participants placed greater emphasis on AI's benefits and comparatively less on risks ($β=-0.337$ for risk and $β=+0.715$ for benefit, $r^2=.839$). Visual cognitive maps illustrate these contrasts, offering new perspectives on how cultural contexts shape AI acceptance. Our findings highlight key factors influencing public perception and provide insights for aligning AI with societal values and promoting equitable and culturally sensitive integration of AI technologies.

Philipp Brauner, Felix Glawe, Gian Luca Liehner et al.

Artificial Intelligence (AI) is reshaping many societal domains, raising critical questions about its risks, benefits, and the potential misalignment between public and academic perspectives. This study examines how the general public (N=1110) -- individuals who interact with or are impacted by AI technologies -- and academic AI experts (N=119) -- those elites shaping AI development -- perceive AI's capabilities and impact across 71 scenarios. These scenarios span domains such as sustainability, healthcare, job performance, societal inequality, art, and warfare. Participants evaluated these scenarios across four dimensions using the psychometric model: likelihood, perceived risk and benefit, and overall value (or sentiment). The results suggest significant differences: experts consistently anticipate higher probabilities, perceive lower risks, report greater benefits, and express more positive sentiment toward AI compared to the non-experts. Moreover, both groups apply different weighting schemes: experts discount risk more heavily relative to benefit than non-experts. Visual mappings of these evaluations uncover areas convergent evaluations (e.g., AI performing medical diagnoses or criminal use) as well as tension points (e.g., decision of legal cases, political decision making), highlighting areas where communication and policy interventions may be needed. These findings underscore a critical translational challenge: if AI research and deployment are to align with societal priorities, the perception gap between developers and the public must be better understood and addressed. Our results provide an empirical foundation for value-sensitive AI governance and trust-building strategies across stakeholder groups.