2 papers
cs.AI2026
LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards
Zhinan Liu, Jie Li, Mingyu Kang +1
Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy. Although latent-reasoning methods reduce to…
cs.CL2026
A Multi-cluster Boundary Learning Method for Out-of-Scope Intent Detection via MiniLM Embedding
Yihong Xu, Mingyu Kang, Linyuan Lü
Intent detection is a critical task that bridges human intents and system actions in human-machine interaction systems. However, there still exist challenges for detecting out-of-s…