AIBullisharXiv – CS AI · Mar 46/102
🧠
ScaleDoc: Scaling LLM-based Predicates over Large Document Collections
ScaleDoc is a new system that enables efficient semantic analysis of large document collections using LLMs by combining offline document representation with lightweight online filtering. The system achieves 2x speedup and reduces expensive LLM calls by up to 85% through contrastive learning and adaptive cascade mechanisms.