Search papers, labs, and topics across Lattice.
This paper introduces User-Aware Active Knowledge Acquisition (UKA), a gradient-free active dialogue learning framework for emotional support dialogue systems that explicitly models uncertainty about user needs. UKA uses a Theory-of-Mind uncertainty estimation to prioritize responses and elicit informative user feedback, enabling efficient exploration of user-aligned conversational knowledge. Experiments on multiple benchmarks show UKA outperforms strong baselines in dialogue quality and user alignment, demonstrating its effectiveness in acquiring relevant conversational knowledge.
Emotional support chatbots can now learn to better understand and respond to your needs by actively probing for information, leading to more helpful and empathetic conversations.
Emotional support plays an important role in dialogue systems, and its success depends on adapting to a user's evolving and implicit needs across multi-turn interactions while leveraging the strong reasoning capacity of large language models. However, since signals about user needs are often weak, indirect, and can only be disambiguated through multi-turn interaction, existing emotional support methods often struggle to acquire and generalize relevant conversational knowledge efficiently. To bridge this gap, we introduce User-Aware Active Knowledge Acquisition (UKA), a gradient-free active dialogue learning framework that explicitly represents uncertainty about user needs and incorporates active learning into both knowledge acquisition and response selection.We propose a Theory-of-Mind uncertainty estimation mechanism that allows the model to prioritize responses, thereby eliciting more informative user feedback. UKA is capable of efficiently exploring user-aligned conversational knowledge during training while maintaining robustness at test time. Experiments across multiple dialogue benchmarks and model architectures demonstrate that our approach consistently outperforms strong baselines in dialogue quality and user alignment.