不用看训练数据，靠分布指纹就能审计大模型微调来源，给AI安全上把锁。
arXiv:2608.02154v1 Announce Type: new Abstract: The proliferation of customized Large Language Models (LLMs) poses critical risks of Data Intellectual…
不用猜测模型为何如此输出，用经验性下一词分布为LLM行为溯源到具体训练数据，看懂这一篇就够了。
arXiv:2607.14306v2 Announce Type: replace Abstract: In this paper, we study the connection between an LLM's output distribution and the data used to t…
自主AI可信度关键：显式溯源机制保障责任伦理，前沿论文剖析Agentic AI治理新范式
arXiv:2605.17169v1 Announce Type: cross Abstract: Agentic AI is rapidly proliferating across diverse real-world domains such as software engineering, …