论文提出 Circuits：将 LLM 分类器组织为自适应查询电路提升成本-精度前沿
Circuits of LLM Classifiers
这篇论文把多个 LLM 分类器的预测串成自适应电路，在七个任务上比 routing 和 cascading 更省成本更准，做分类系统的可以看看。
arXiv 论文将 LLM 分类器视为对目标标签的含噪测量仪器，目标是在给定平均查询成本下最大化分类准确率。作者提出 circuits 结构，把不同模型的分类预测组织为自适应的查询与决策序列，并刻画了最优电路和可达准确率的理论极限。在覆盖安全、健康、政治学、人类偏好、智能体评估、决策与推理的七个分类任务上，该方法在成本-精度前沿上优于 routing 和 cascading 基线。
Circuits of LLM Classifiers
Language models make it easy to build classifiers by simply prompting a model with the sample to classify. However, their predictions are neither deterministic nor uniformly reliable across samples. How can we combine predictions from different models to improve reliability? We view LLM classifiers as noisy measurement instruments of an underlying target label. Our goal is to maximize average classification accuracy at a given average query cost. To this end, we introduce circuits that organize LLM classifiers into an adaptive sequence of queries and decisions. We then characterize the optimal circuit, obtain the fundamental limits of achievable accuracy, and provide practical insights on realizing the optimal circuit. Across seven classification tasks spanning safety, health, political science, human preference, agent evaluation, decision-making and reasoning, our method improves the cost-accuracy frontier over routing and cascading baselines.