LLM 驱动卫星振动测试分析:校验门控让 20/20 配置与人工结果完全一致
Language Models Meet Vibration Testing for LEO Constellation Satellites with Calibrated Response Prediction from Few-show Sweeps
做工程自动化的开发者值得看:LLM 读中文测试记录提配置,靠单位检查加双模型交叉验证把关,20 个案例结果和人工跑的逐位一致。还诚实报告了 LLM 预测曲线不如小型物理网络的边界,比多数只报喜的论文实在。
一篇 arXiv 论文提出“确定性校验门控”范式,用于约束 LLM 驱动的工程分析:LLM 产出的类型化配置必须先通过单位检查、物理一致性、逐字引用核对、双模型交叉验证、与测量导出数据比对等确定性检查后才被数值程序消费。门控从两个方向拦截幻觉——引用检查抓捏造内容,模型交叉验证抓引用检查漏掉的遗漏错误。
作者将该范式实例化在低轨巨型星座卫星的正弦振动验收测试上:DeepSeek V4.1 Flash 和 Qwen-plus 读取中文测试记录,提取 76 个字段的配置。五个输入变体上事实级 F1 达 0.98 到 1.0;全部门控开启时,20 个配置的 notching 结果与 gold run 逐位一致,17 个真实和注入错误全部被拦截,其中 16 个在没有门控时本会直接运行。
论文还给出一个有实用价值的负面结果:LLM 直接做曲线预测只达到线性外推水平,而小型物理结构化网络在覆盖率 c=0.90 下将过抑制带宽降低 86% 到 89%,划清了 LLM 直接预测应让位于训练模型的边界。
Language Models Meet Vibration Testing for LEO Constellation Satellites with Calibrated Response Prediction from Few-show Sweeps
Large language models (LLMs) increasingly drive engineering analysis end to end, turning textual records into the inputs of numerical programs, but a plausible and wrong value can pass silently into a decision. We propose deterministic validation gates for LLM-driven engineering analysis, a general paradigm in which a typed configuration produced by LLMs is consumed only after it passes deterministic checks on units, physical consistency, verbatim quotes, agreement between independent models, consistency with measurement exports and the applicability of trained models. The gates target hallucinations from two directions, since quote checking catches fabricated content while agreement between models catches errors of omission that quote checking misses. We instantiate the paradigm on sine vibration acceptance testing for low Earth orbit mega-constellation satellites, where DeepSeek V4.1 Flash and Qwen-plus read Chinese test records and extract a configuration of 76 fields. Fact-level F1 ranged from 0.98 to 1.0 on five input variants, with all repairs frozen on development inputs and evaluated on held-out inputs. With all gates, 20 of 20 configurations produced notching results bit for bit identical to the gold run, and all 17 real and injected errors in consumed fields were stopped, of which 16 would have run without gates. Retraining the bound model on a dataset built from an LLM configuration reproduced its results within GPU nondeterminism. We also report a negative result of practical value. Direct LLM curve forecasting only matches linear extrapolation, whereas a small physics-structured network reduces the over-notched bandwidth by 86% to 89% at calibrated coverage c = 0.90, which delineates where direct LLM prediction should give way to a trained model.
This report is categorized under AITOP's "Papers" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include DeepSeek, Qwen, LLM, AI safety.
Source attribution: curated from arXiv cs.AI (@Jun Wu, Deming Li, Zhenming Zheng, Honghao Yue, Fei Yang, Hao Sun).