The Last Harness You'll Ever Build
Paper • 2604.21003 • Published • 6
Haebin Seong PRO
hbseong
AI & ML interests
None yet
Recent Activity
authored a paper about 2 months ago
The Last Harness You'll Ever Build upvoted a paper about 2 months ago
The Last Harness You'll Ever Build submitted a paper about 2 months ago
The Last Harness You'll Ever BuildOrganizations
upvoted a paper about 2 months ago
upvoted a paper 9 months ago
upvoted 3
papers over 1 year ago
SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
Paper • 2502.12464 • Published • 28
Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems
Paper • 2410.13334 • Published • 12
HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
Paper • 2410.01524 • Published • 3