The Other Side of the Conversation: Learning Behavioral User Models from User-Side Turns

Conversational intelligence requires an assistant to not only respond to what is said, but to anticipate how a particular interlocutor is likely to respond. But can LLMs construct such a user model from dialogue alone? We study this question in a controlled setting where a synthetic user is defined by a combination of persona and style, encoded in a known system prompt $P$. We evaluate how well three strategies can approximate $P$ by only observing conversations, without having access to $P$: 1) conditioning on demonstrations in context, 2) explicitly reconstructing a natural-language description of the user, and 3) learning a continuous soft prompt from user-generated turns. Our evaluation shows that these conversation-only methods recover a substantial amount of user-specific signal. However, fidelity to the user depends on the criterion we apply: distributional agreement, recovery of persona and style, or how reliably generated text is judged to come from a user. Our framework provides a quantitative way to evaluate user simulation from dialogue and its limits.