Learning Steerable Clarification Policies with Collaborative Self-play
Jonathan Berant · Maximillian Chen · Adam Fisch · Reza Aghajani · Fantine Eri Huot · Mirella Lapata · Jacob Eisenstein
AI models should change how they clarify ambiguous prompts based on context, their confidence and interaction cost. We train steerable LMs that take cost coefficients as input and choose a clarification policy that maximizes cost-conditioned reward.
摘要
To handle ambiguous queries, AI assistants must decide (a) when to guess the user's intent and answer directly, (b) when to enumerate and respond to multiple plausible intents, and (c) when to ask a clarifying question. No strategy is always superior; the right decision depends on *contextual* factors such as user preferences or modality. For example, enumerating several possible interpretations can be cumbersome on small screens or voice-based settings, while a more interactive style may be dispreferred in desktop settings. In this work, we propose training *steerable policies* for managing such uncertainty via self-play. Given two agents, one simulating a user and the other an AI assistant, we generate conversations where the user issues a potentially ambiguous query, and the assistant must choose how to respond. The assistant receives as input the *numerical cost* of asking a clarification question, and of generating each word, and is trained to select the conversational action that maximizes its final reward: accuracy penalized by these costs. We apply Reinforced Self-Training (ReST) to optimize this objective and show that it yields a steerable policy that adapts its behavior based on the provided costs, improving both reward and accuracy. Moreover, the resulting policy generalizes to numerical cost values unobserved during training.