User representations improve AI assistant simulation fidelity and diversity
Learning User Representations to Improve Simulation Fidelity
Computation and Language
Summary
AI assistants are trained using simulated users, but these simulators often fail to mimic real people accurately, especially less common user types. The authors show that better descriptions of users, called user representations, help simulators act more like real users. They created a method to improve these representations by comparing simulated conversations to the original ones and using that feedback to make the descriptions better. Their improved system, UserRepGen-4B, generates user representations that lead to more realistic and diverse simulated users across many tasks.
What this means in practice
- •For ai assistant developers: Generate more accurate user models that improve training and evaluation of AI assistants across diverse user behaviors.
- •For dialog system designers: Create simulators that better reflect real user diversity and unseen tasks, improving system robustness and user experience.
- •For customer service platform teams: Enhance virtual customer interaction simulations with realistic user behavior for better agent training and testing.$Commercial implications: It enables commercial virtual customer assistant products that generalize well to diverse, real-world users.
Authors
Shuhaib Mehri, Philippe Laban, Michel Galley, Dilek Tür, Jennifer Neville, Jianfeng Gao
Abstract
User simulators enable interactive training and evaluation of AI assistants at scale. Yet current simulators struggle to reproduce the diverse behaviors of real users, leading to assistants that generalize poorly to underrepresented users. We identify user representations as an underexplored bottleneck in user simulation. User representations are natural-language descriptions that condition simulators to reproduce a particular user's behavior. A representation's quality becomes apparent in hindsight, through the behavior it induces in a simulator. To evaluate and optimize user representations, we formulate a conversation reconstruction task: given an original conversation, we generate a representation, condition a simulator on it, simulate a conversation, and then measure fidelity by comparing user behavior in the original and simulated conversations. This comparison also yields hindsight feedback, which identifies where the representation falls short and how it can be improved. We introduce hindsight distillation, an online training procedure that distills feedback-conditioned improvements into the representation generator, enabling it to generate improved representations directly from the original conversation. We present UserRepGen-4B, a representation generator trained with hindsight distillation. Across 700 conversations spanning seven datasets, hindsight feedback helps improve user representations at test time, and UserRepGen-4B generates representations that enable more faithful simulation than those generated by GPT-5.5. Beyond conversation reconstruction, learned representations improve simulation fidelity for unseen tasks, better preserve the population-level diversity of real users, and better distinguish users across conversations.