ScaleDoc: Scaling LLM-based Predicates over Large Document Collections

Predicates are foundational components in data analysis systems. However, modern workloads increasingly involve unstructured documents, which demands semantic understanding, beyond traditional value-based predicates. Given enormous documents and ad hoc queries, while Large Language Models (LLMs) demonstrate powerful zero-shot capabilities, their high inference cost leads to unacceptable overhead. Therefore, we introduce ScaleDoc, a novel system that addresses this by decoupling predicate execution into an offline representation phase and an optimized online phase. In the offline phase, ScaleDoc leverages a LLM to generate semantic representations for each document. Online, for each query, it adaptively trains a lightweight proxy model on these representations to filter the majority of documents, forwarding only the ambiguous cases to the LLM for final decision. Furthermore, ScaleDoc proposes two core innovations to achieve significant efficiency: (1) a contrastive-learning-based framework that trains the proxy model to generate reliable predicating decision scores; (2) an adaptive cascade mechanism that determines the effective filtering policy while meeting specific accuracy targets. Our evaluations across three datasets demonstrate that ScaleDoc achieves over a 2× end-to-end speedup and reduces expensive LLM invocations by up to 85%, making large-scale semantic analysis practical and efficient.