Mental models play an important role in whether user interactions with intelligent systems, such as dialog agents, are successful. Adaptive dialog systems present the opportunity to align a dialog agent’s behavior with heterogeneous user expectations. However, there has been little research into what mental models users form when interacting with a task-oriented dialog system, how these models affect users’ interactions, or what role system adaptation can play in this process. This can make it challenging to avoid damage to human-AI partnership. In this work, we collect a new publicly available dataset for exploring user mental models of information seeking dialog systems. We demonstrate that users have a variety of conflicting mental models about such systems, the validity of which directly impacts the success and perception of their interactions. Furthermore, we show that adapting a dialog agent’s behavior to better align with users’ mental models, even when done implicitly, can improve dialog efficiency, success, and user perception of the interaction. This shows that implicit adaptation can be beneficial for task-oriented dialog systems, so long as developers understand the mental models of their users.