analiza aiqbench
CacheRAG addresses a critical inefficiency in current Retrieval-Augmented Generation (RAG) systems by introducing a semantic cache that transforms stateless planners into continual learners, thereby reducing schema hallucinations and improving retrieval coverage. The architecture leverages a two-stage semantic parsing framework and diversity-optimized retrieval to balance natural language accessibility with safe, bounded query execution. Experimental results indicate significant gains in accuracy and truthfulness, suggesting this approach offers a viable path toward more robust knowledge graph question answering without relying on frequency-based caching alone.
CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering
arXiv:2604.26176v3 Announce Type: replace-cross Abstract: The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answering (KGQA). However, existing LLM-driven KGQA systems act as stateless planners, generating retrieval plans in isolation without exploiting historical query patterns: analogous to a database system that optimizes every query from scratch without a plan cache. This fundamental design flaw leads to schema hallucinations and limited retrieval coverage. We propose CacheRAG, a systematic cache-augmented architecture for LLM-based KGQA that transforms stateless planners into continual learners. Unlike traditional database plan caching (which optimizes for frequency), CacheRAG introduces three novel design principles tailored for LLM contexts: (1) Schema-agnostic user interface: A two-stage semantic parsing framework via Intermediate Semantic Representation (ISR) enables non-expert users to interact purely in natural language, while a Backend Adapter grounds the LLM with local schema context to compile executable physical queries safely. (2) Diversity-optimized cache retrieval: A two-layer hierarchical index (Domain $\rightarrow$ Aspect) coupled with Maximal Marginal Relevance (MMR) maximizes structural variety in cached examples, effectively mitigating reasoning homogeneity. (3) Bounded heuristic expansion: Deterministic depth and breadth subgraph operators with strict complexity guarantees significantly enhance retrieval recall without risking unbounded API execution. Extensive experiments on multiple benchmarks demonstrate that CacheRAG significantly outperforms state-of-the-art baselines (e.g., +13.2% accuracy and +17.5% truthfulness on the CRAG dataset).
Abstract:The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answering (KGQA). However, existing LLM-driven KGQA systems act as stateless planners, generating retrieval plans in isolation without exploiting historical query patterns: analogous to a database system that optimizes every query from scratch without a plan cache. This fundamental design flaw leads to schema hallucinations and limited retrieval coverage. We propose CacheRAG, a systematic cache-augmented architecture for LLM-based KGQA that transforms stateless planners into continual learners. Unlike traditional database plan caching (which optimizes for frequency), CacheRAG introduces three novel design principles tailored for LLM contexts: (1) Schema-agnostic user interface: A two-stage semantic parsing framework via Intermediate Semantic Representation (ISR) enables non-expert users to interact purely in natural language, while a Backend Adapter grounds the LLM with local schema context to compile executable physical queries safely. (2) Diversity-optimized cache retrieval: A two-layer hierarchical index (Domain $\rightarrow$ Aspect) coupled with Maximal Marginal Relevance (MMR) maximizes structural variety in cached examples, effectively mitigating reasoning homogeneity. (3) Bounded heuristic expansion: Deterministic depth and breadth subgraph operators with strict complexity guarantees significantly enhance retrieval recall without risking unbounded API execution. Extensive experiments on multiple benchmarks demonstrate that CacheRAG significantly outperforms state-of-the-art baselines (e.g., +13.2% accuracy and +17.5% truthfulness on the CRAG dataset).
Databases (cs.DB); Computation and Language (cs.CL)
arXiv:2604.26176 [cs.DB]
(or arXiv:2604.26176v3 [cs.DB] for this version)
Text integral sub licența deschisă a publicației · 227 cuvinte
Subiecte conexe
CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering
arXiv · 9 iun. 2026
AWS vector solutions: Build agentic AI where your data lives
AWS · 20 aug. 2026
12 Ways to Reduce LLM Latency and Inference Costs in Production
KDnuggets · 14 iul. 2026
Democratizing institutional knowledge: Building an AI-powered knowledge management system with AWS
AWS · 24 aug. 2026