Knowledge Conceptualization Impacts RAG Efficacy
This work addresses the challenge of designing transferable and interpretable neurosymbolic AI systems for AI agents, but it appears incremental as it builds on existing RAG frameworks without introducing a new paradigm.
The paper systematically evaluates how different conceptualizations and representations of knowledge affect the efficacy of Agentic Retrieval-Augmented Generation systems in querying a triplestore, finding that both structure and complexity have significant impacts.
Explainability and interpretability are cornerstones of frontier and next-generation artificial intelligence (AI) systems. This is especially true in recent systems, such as large language models (LLMs), and more broadly, generative AI. On the other hand, adaptability to new domains, contexts, or scenarios is also an important aspect for a successful system. As such, we are particularly interested in how we can merge these two efforts, that is, investigating the design of transferable and interpretable neurosymbolic AI systems. Specifically, we focus on a class of systems referred to as ''Agentic Retrieval-Augmented Generation'' systems, which actively select, interpret, and query knowledge sources in response to natural language prompts. In this paper, we systematically evaluate how different conceptualizations and representations of knowledge, particularly the structure and complexity, impact an AI agent (in this case, an LLM) in effectively querying a triplestore. We report our results, which show that there are impacts from both approaches, and we discuss their impact and implications.