Ventor-QTest：威胁模型驱动的供应商托管LLM API验证

摘要

随着大语言模型日益普及，部署开放权重模型的第三方提供商已成为生态系统的重要组成部分。因此，审计其推理API的质量是一个开放问题。我们将托管模型路由形式化为随机过程，并提出\textbf{Ventor-QTest}，一种无需目标API提供任何概率信息的复合黑盒审计方法。其重复请求组件将每个冻结的受限上下文多次发送至目标，根据返回的文本计数重建类别输出分布，并报告平均保真度损失(AFL)，作为零偏校正的窗口内平均粗化KL统计量。其长序列组件使用独立运行，通过运行级参考中心惊讶度统计量的经验上尾报告极端保真度损失(EFL)。在三个支持logprob的路由条件下，AFL与基于logprob的粗化KL比较器表现出强烈的线性描述性一致性。在七个路由快照中，20次运行的序列探针揭示了特定于路由的EFL变化。AFL和EFL与GPQA-Diamond准确率之间几乎不存在可检测的路由级关联。相反，随着任务暴露程度的增加，显著的EFL与Terminal-Bench通过率下降同时出现。这一模式可能源于长时程任务中正确性对极端保真度损失更为敏感。这些结果支持联合报告AFL和EFL，尤其是在审计长时程智能体任务时。开源实现可在https://github.com/Tencent/AI-Infra-Guard/tree/main/services/api_checker/ventor_qtest获取。

English

As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the ecosystem. Auditing the quality of their inference APIs is therefore an open problem. We formalize hosted model routing as a stochastic process and propose \textbf{Ventor-QTest}, a composite black-box audit that requires no probability information from the target API. Its repeated-request component sends each frozen constrained context to the target multiple times, reconstructs a categorical output distribution from the returned text counts, and reports average fidelity loss (AFL) as a null-bias-corrected, within-window mean coarsened-KL statistic. Its long-sequence component uses independent runs to report extreme fidelity loss (EFL) through the empirical upper tail of a run-level reference-centered-surprisal statistic. Across three logprob-capable route conditions, AFL shows strong linear descriptive agreement with a logprob-derived coarsened-KL comparator. Across seven route snapshots, 20-run sequence probes reveal route-specific EFL variation. AFL and EFL have little detectable route-level association with GPQA-Diamond accuracy. In contrast, pronounced EFL coincides with a decline in Terminal-Bench pass rate as task exposure increases. This pattern may arise because correctness in long-horizon tasks is more sensitive to extreme fidelity loss. These results motivate reporting AFL and EFL jointly, particularly when auditing long-horizon agentic tasks. The open-source implementation is available at https://github.com/Tencent/AI-Infra-Guard/tree/main/services/api_checker/ventor_qtest.