This content will become publicly available on August 11, 2025
SafeDecoding: Defending against jailbreak attacks via safety-aware decoding
- Award ID(s):
- 2229876
- NSF-PAR ID:
- 10524896
- Publisher / Repository:
- Annual Meeting of the Association for Computational Linguistics (ACL)
- Date Published:
- Format(s):
- Medium: X
- Location:
- Bangkok, Thailand
- Sponsoring Org:
- National Science Foundation
More Like this
No document suggestions found