2 papers
cs.LG2026
DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment
Yi Nian, Tiankai Yang, Yudi Zhang +7
Safety alignment for large language models relies on preference data, but current pipelines often train on large, redundant datasets. Existing data selection methods typically scor…
cs.AI2026
When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Auditing
Yi Nian, Haosen Cao, Shenzhe Zhu +4
When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? In practice, generated content is oft…