Invited Talk 4: Solving the Specification Problem through Interaction (Belinda Zou Li)

AI systems must act on queries that are often underspecified, ambiguous, or missing information necessary to respond well. Yet today’s language models are typically trained on static data and lack principled mechanisms for recognizing what they don’t know and acquiring it through interaction. In this talk, I will present a line of work on building language models that resolve this incompleteness by asking the right questions. I’ll begin with work that trains models to ask targeted follow-up questions that efficiently infer users’ latent preferences, outperforming static prompting and survey-style approaches. I’ll then describe follow-up work that formulates preference elicitation in a Bayesian decision-theoretic framework, equipping language models with an explicit Bayesian user model. Finally, I’ll introduce QuestBench, a benchmark for evaluating interactive question-asking behavior in controlled environments. Together, these results outline a path toward language models that recognize the limits of their own knowledge and resolve it through natural interaction, enabling more reliable, personalized, and collaborative AI systems.