Navigating the Conceptual Multiverse

Abstract:When language models answer open-ended questions, they implicitly make decisions that shape their answers. However, the models do not show these decisions to the user, so users cannot contextualize answers: they cannot see the assumptions an answer rests on or the alternatives to it. Drawing on multiverse analysis from statistics, we introduce the conceptual multiverse, a representation in which language models express answers as the result of intermediate conceptual decisions. We build a system that generates such decisions explicitly, organizes them into a space of answers that users can see and change, and checks them against the norms of a specific domain. In a user study across three domains - philosophy, AI alignment annotation, and poetry - participants say that our system helps them see the decisions leading to an answer, explore the space of answers, and understand the decisions structuring this space.

Human-Computer Interaction (cs.HC); Computation and Language (cs.CL); Computers and Society (cs.CY)

arXiv:2604.17815 [cs.HC]

(or arXiv:2604.17815v4 [cs.HC] for this version)

https://doi.org/10.48550/arXiv.2604.17815 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.