Neuro-Symbolic Query Compiler
This addresses the challenge of handling complex queries in RAG systems, which is incremental as it builds on existing neuro-symbolic and compiler design approaches.
The paper tackles the problem of precise search intent recognition in Retrieval-Augmented Generation (RAG) systems for complex queries with nested structures, presenting QCompiler, a neuro-symbolic framework that compiles queries into Abstract Syntax Trees (ASTs) to improve document retrieval and response generation.
Precise recognition of search intent in Retrieval-Augmented Generation (RAG) systems remains a challenging goal, especially under resource constraints and for complex queries with nested structures and dependencies. This paper presents QCompiler, a neuro-symbolic framework inspired by linguistic grammar rules and compiler design, to bridge this gap. It theoretically designs a minimal yet sufficient Backus-Naur Form (BNF) grammar $G[q]$ to formalize complex queries. Unlike previous methods, this grammar maintains completeness while minimizing redundancy. Based on this, QCompiler includes a Query Expression Translator, a Lexical Syntax Parser, and a Recursive Descent Processor to compile queries into Abstract Syntax Trees (ASTs) for execution. The atomicity of the sub-queries in the leaf nodes ensures more precise document retrieval and response generation, significantly improving the RAG system's ability to address complex queries.