Future research questions for mental models in contemporary AI

Investigate whether mental-model elicitation results can be meaningfully compared within and across studies; determine the assumptions underlying different elicitation methods; characterize how contemporary AI systems challenge existing assumptions about mental models and their elicitation; identify suitable classes of methods for contemporary AI systems; distinguish the mental-model construct from adjacent constructs such as folk theories, sensemaking, schemata, and anthropomorphism; develop ways to capture the evolution of mental models through interaction with a system; and determine what insights mental-model elicitation provides for intelligent-user-interface design and whether those insights can be obtained through other approaches.

Background

The workshop is organized around methodological and conceptual challenges in studying mental models of generative and agentic AI systems. The authors identify heterogeneity in elicitation practices, uncertainty about the boundaries of the mental-model construct, and the possibility that adaptive and opaque AI systems undermine assumptions inherited from earlier human-computer interaction research.

During the breakout discussions, participants are explicitly assigned different open questions concerning the future of mental-model research. These questions address comparability across elicitation studies, the suitability of methods for contemporary AI systems, conceptual distinctions from related constructs, the dynamic evolution of mental models, and the design value of elicitation. The paper presents these as unresolved questions for discussion rather than claims resolved by the workshop proposal.

References

Participants will be assigned to breakout groups, each focusing on a different open question concerning the future of mental model research in the context of contemporary AI systems. Groups will draw on insights from the presentation, the elicitation exercise, and their own research experience. The goal is not necessarily to reach consensus, but to articulate competing perspectives and promising research directions. The questions under consideration are, and are not limited to: Q1. Operationalization methods. Can mental model elicitations be meaningfully compared within and across studies? What assumptions underlie different elicitation methods? Q2. Contemporary AI systems. How do contemporary AI systems challenge existing assumptions about mental models and their elicitation? What are (un)suitable class of methods for these systems? Q3. Conceptual boundaries. What makes the mental model construct distinctive from adjacent constructs such as folk theories, sensemaking, schemata, and anthropomorphism? Q4. Dymanics. How can researchers capture the dynamic nature of mental models given mental models continue to evolve through interaction with a system? Q5. Research and design value. What insights does mental model elicitation provide for the design of intelligent user interfaces? Could they be obtained through other approaches?

— [MM/AI] Mental Models in Human-AI Interaction: Methods and Challenges in the Generative and Agentic AI Era (Workshop)  (2609.17206 - Sanchez et al., 15 Sep 2026) in Section 'Workshop activities', subsection 'Breakout discussions'