Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing
Wenhao Liu, Siyu An, Junru Lu, Muling Wu, Tianlong Li, Xiaohua Wang, Changze Lv, Xiaoqing Zheng, Di Yin, Xing Sun, Xuanjing Huang. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
Authors
- Xing Sun (ORCID: https://orcid.org/0000-0001-8132-9083)
- Xiaoqing Zheng (ORCID: https://orcid.org/0000-0003-4430-5036)
- Tianlong Li (ORCID: https://orcid.org/0000-0002-9483-457X)
- Siyu An (ORCID: https://orcid.org/0009-0008-6004-7325)
- Junru Lu (ORCID: https://orcid.org/0009-0004-9588-8766)
- Wenhao Liu (ORCID: https://orcid.org/0000-0001-9757-1077)
- Xiaohua Wang (ORCID: https://orcid.org/0000-0002-6551-151X)
- Di Yin (ORCID: https://orcid.org/0000-0002-3272-9643)
- Xuanjing Huang
- Muling Wu
- Changze Lv
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.findings-acl.311
- Primary Topic
- Multi-Agent Systems and Negotiation
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China