摘要：决策模型（Decision models）作为一种仅针对调用方提供的选项输出概率分布、不生成任何文本的非生成式评分器，正日益广泛地作为路由器（routers）、分类器和安全护栏（guardrails）进行部署。由于它们不生成任何内容，因此思维链（chain-of-thought）和推理阐述并不适用。我们完全通过对其输入进行干预，审查了三类模型：编码器评分器（encoder scorer）、解码器评分器（decoder scorer）以及闭源 API，评估基于专家标注的、带有标准比喻义和标准字面义释义的孟加拉语成语。

当把成语自身的字面释义放入候选项列表中时，所有测试模型分支都会被其吸引，这占到了各模型在孟加拉语下剩余错误的 65% 至 96%。在一个共享项目集上构建的模型-语言矩阵显示，这一现象在多大程度上取决于测试语言：在完全相同的配对条目上，所有模型分支在孟加拉语下被字面义捕获的概率是英语的 1.9 到 6.4 倍；商业模型表现出的所谓抵御能力实际上只是其测试语言带来的一种特性，整体能力的高低并不能改变这种失效规律。

三个模型分支的模型校准度（calibration）均出现恶化，且在开源模型分支中置信度发生了倒置——基于置信度进行阈值过滤（gating）的效果甚至比随机过滤更差。在准确率处于随机猜测水平的无语义选项列表中，校准度表现最好的模型分支报告的平均置信度依然高达 0.82。代码与数据：此 GitHub 链接。

Abstract:Decision models, non-generative scorers that report a probability over caller-supplied options and emit no text, are increasingly deployed as routers, classifiers and guardrails. Because they generate nothing, rationales and chain-of-thought do not apply. We audit three: an encoder scorer, a decoder scorer and a closed API, entirely through interventions on their input, using expert-annotated Bengali idioms carrying a gold figurative and a gold literal gloss. Dropping an idiom's own literal gloss into the option list draws every arm toward it, taking 65% to 96% of each arm's remaining Bengali errors. A model-by-language matrix over one shared item set shows how far this depends on the test language: every arm is 1.9 to 6.4 times more captured in Bengali than in English on the same paired entries, the commercial model's apparent resistance is a property of its test language, and capability does not order the failure. Calibration degrades in all three arms, and on the open arms confidence inverts, so gating on it is worse than gating at random. On a semantics-free option list, where accuracy is at chance, the best-calibrated arm still reports mean confidence 0.82. Code and data: this https URL.