User-Aware Active Knowledge Acquisition for Emotional Support Dialogue
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913170066505728 |
|---|---|
| author | Xu, Mufan Chen, Kehai Hu, Jiahao Xu, Xinchao Yang, Muyun Zhao, Tiejun Zhang, Min |
| author_facet | Xu, Mufan Chen, Kehai Hu, Jiahao Xu, Xinchao Yang, Muyun Zhao, Tiejun Zhang, Min |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29715 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | User-Aware Active Knowledge Acquisition for Emotional Support Dialogue Xu, Mufan Chen, Kehai Hu, Jiahao Xu, Xinchao Yang, Muyun Zhao, Tiejun Zhang, Min Computation and Language 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. |
| title | User-Aware Active Knowledge Acquisition for Emotional Support Dialogue |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.29715 |