1
TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles
ACL 2026论文:用轻量级专家集成方法,解决大模型不可验证约束对齐难题,提升安全性与可控性。
arXiv:2606.07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse const…