HyCoRA: Hyper-Contrastive Role-Adaptive Learning for Role-Playing
Shihao Yang, Zhicong Lu, Yong Yang, Bo Lv, Yang Shen, Nayu Liu

TL;DR
HyCoRA introduces a novel hyper-contrastive role-adaptive learning framework that balances role-specific and shared traits, significantly enhancing multi-character role-playing in language models.
Contribution
The paper proposes a Hyper-Half Low-Rank Adaptation structure with a hyper-contrastive mechanism to better model distinct and shared role traits, improving role-playing abilities.
Findings
Outperforms existing methods on English and Chinese benchmarks.
Effectively captures role-specific personality signatures.
Validated by GPT-4 evaluations and visual analyses.
Abstract
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 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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsMultimodal Machine Learning Applications · Machine Learning in Healthcare · Topic Modeling
