前沿大型语言模型在网络权重审计中的表现
Frontier large language models (LLMs) have been reported to read, edit and write the weights of small neural networks, raising the prospect of auditing clinical prediction models from their files alone.
Public demonstrations, however, mixed reading raw weights with running code.
实验设计与模型设置
We separated these conditions in internally pre-specified simulation experiments. Tanh networks of 105 to 38,401 weights were trained on simulated cohorts of patients with subarachnoid haemorrhage, each with a planted relationship or none, and one network was trained on labels that under-recorded deaths in a subgroup. GPT-6 Astra and four other GPT models answered single prompts under a default or an explicit system instruction, either with the weights in the prompt and no tools, or with a calculation-only tool that exposed the weights (white box) or only the network's predictions (black box).
- 在 Prompt 中直接提供底层权重，不使用任何辅助工具
- 使用仅用于计算的工具，但工具会暴露权重（白盒）
- 使用工具，但工具仅暴露网络的预测结果（黑盒）
研究结果与关键发现
Without tools, Astra recovered planted relationships in 353-weight networks but became unreliable at 3,457 weights, and under the default instruction it declined 11 of 12 audit and repair tasks as unidentifiable; the explicit instruction removed these refusals.