GitHub · HTML
CosmosYi/ReasoningShield
[NeurIPS 2026] ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models
- Stars
- 61
- Forks
- 2
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: ai-safety, detection, llm, moderation, reasoning-models, safety, neurips-2026
Latest data point: Nov 21, 2026 · 61 stars · 2 forks