EUVIMEDEUVIMED entdecken
Crossref

HyCoRA: Hyper-Contrastive Role-Adaptive Learning for Role-Playing

Shihao Yang, Zhicong Lu, Yong Yang, Bo Lv, Yang Shen, Nayu Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (40) · 34304-34312

DOI: 10.1609/aaai.v40i40.40727 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shihao Yang und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-character role-playing aims to equip models with the capability to simulate diverse roles. Existing methods either use one shared parameterized module across all roles or assign a separate parameterized module to each role. However, the role-shared module may ignore distinct traits of each role, weakening personality learning, while the role-specific module may overlook shared traits across multiple roles, hindering commonality modeling. In this paper, we propose a novel HyCoRA: Hyper-Contrastive Role-Adaptive learning framework, which efficiently improves multi-character role-playing agents' ability by balancing the learning of distinct and shared traits. Specifically, we propose a Hyper-Half Low-Rank Adaptation structure, where one half is a role-specific module generated by a lightweight hyper-network, and the other half is a trainable role-shared module. The role-specific module is devised to represent distinct persona signatures, while the role-shared module serves to capture common traits. Moreover, to better reflect distinct personalities across different roles, we design a hyper-contrastive learning mechanism to help the hyper-network distinguish their unique characteristics. Extensive experimental results on both English and Chinese available benchmarks demonstrate the superiority of our framework. Further GPT-4 evaluations and visual analyses also verify the capability of HyCoRA to capture role characteristics.

Zitieren

APA

Yang, S., Lu, Z., Yang, Y., Lv, B., Shen, Y., & Liu, N. (2026). HyCoRA: Hyper-Contrastive Role-Adaptive Learning for Role-Playing. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 34304-34312. https://doi.org/10.1609/aaai.v40i40.40727

Vancouver

Yang S, Lu Z, Yang Y, Lv B, Shen Y, Liu N. HyCoRA: Hyper-Contrastive Role-Adaptive Learning for Role-Playing. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(40):34304-34312. doi:10.1609/aaai.v40i40.40727

BibTeX
@article{Yang2026,
  author = {Yang, Shihao and Lu, Zhicong and Yang, Yong and Lv, Bo and Shen, Yang and Liu, Nayu},
  title = {HyCoRA: Hyper-Contrastive Role-Adaptive Learning for Role-Playing},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {40},
  pages = {34304--34312},
  doi = {10.1609/aaai.v40i40.40727}
}
Kostenlos starten →