DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance
arXiv:2608.14644v1 Announce Type: new Abstract: Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant. Conventional post-training is structurally ill-suited: SFT hides the violation signal in compliant labels, and DPO's sequence-level preferences mismatch token-localized violations. We propose DUET, a token-selective on-policy distillation method for prohibition compliance. DUET pair...
arXiv cs.LG
·Zihan Li, Feifei Li, Wenhui Que
·
// relacionados
Leia também
Blog
Flight attendants freaked out that Google is buying tons of Spirit employee data
Blog
Attackers are using AI to build exploits for industrial control systems, U.S. agencies warn
Blog
AI labs are failing to keep their own systems in check
Editorial