Ihor Stepanov
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1NLP×1
Frequent co-authors
Research Timeline
2026
Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content
The paper introduces Opir, an efficient family of encoder-based multi-task guardrail models that provides competitive safety classification performance across various tasks while maintaining a significantly smaller deployment footprint than existing large guardrail models.
Highlighted terms show continued research focus across papers