RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue
Speech-to-speech dialogue models increasingly support persona control, yet existing spoken role-playing benchmarks remain largely character-centric and short-horizon. This leaves open whether spoken dialogue models can sustain diverse roles over extended interactions, especially beyond predefined fictional characters. We introduce RoleBreak, an open benchmark for long-horizon role-playing robustness in spoken dialogue. RoleBreak contains 310 character-based and user-centered roles, 6,688 human-verified dialogue turns, and 11,743 fine-grained evaluation criteria, with 1,856 turns carrying expressive emotion targets for evaluating vocal emotion. Its scenarios are designed to stress role con...
| Authors | Yuqi Wang, Fengyuan Liu, Haochen Luo et al. |
|---|---|
| Primary category | cs.CL |
| Published | 15 September 2026 |
| Last updated at source | 15 September 2026 |
Models and datasets referencing this paper
- Greenbean/RoleBreakDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.