Rationalize: Shared Semantic Reasoning for Human-AI Alignment
This framework addresses the problem of human-AI alignment for researchers and practitioners developing collaborative AI systems, offering a conceptual model for deeper interaction beyond mere output alignment.
This paper introduces Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking. It conceptualizes human-AI interaction as complementary role pairs (Explorer-Guide, Investigator-Informant, Teacher-Student, Judge-Advocate) to facilitate alignment at the level of rationalization of intent and action, not just output.
We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking. Building on ideas in human-machine teaming and critical thinking, we conceptualize human-AI interaction as a series of complementary role pairs (Explorer-Guide, Investigator-Informant, Teacher-Student, Judge-Advocate) operating in a shared reasoning space. In this space, human analysts and AI models (such as LLMs) make purposes, questions, assumptions, evidence, inferences, and implications explicit, facilitating alignment not only at the output level but at the level of rationalization of intent and action by each side. We relate these role pairs to the bidirectional human-AI alignment framework, illustrating how "aligning AI to humans" and "aligning humans to AI" differ by role, and sketch a collaborative research agenda for alignment design and assessment using element-level and role-specific approaches.