Parallel and Multi-Stage Knowledge Graph Retrieval for Behaviorally Aligned Financial Asset Recommendations
This work addresses the challenge of deploying grounded financial AI in resource-constrained environments, offering an incremental improvement over prior methods.
The paper tackles the problem of improving personalized financial recommendations by addressing context limits, hallucinations, and lack of behavioral grounding in LLMs, introducing RAG-FLARKO, which enhances recommendation quality through multi-stage and parallel KG retrieval, enabling smaller models to achieve high performance in profitability and behavioral alignment.
Large language models (LLMs) show promise for personalized financial recommendations but are hampered by context limits, hallucinations, and a lack of behavioral grounding. Our prior work, FLARKO, embedded structured knowledge graphs (KGs) in LLM prompts to align advice with user behavior and market data. This paper introduces RAG-FLARKO, a retrieval-augmented extension to FLARKO, that overcomes scalability and relevance challenges using multi-stage and parallel KG retrieval processes. Our method first retrieves behaviorally relevant entities from a user's transaction KG and then uses this context to filter temporally consistent signals from a market KG, constructing a compact, grounded subgraph for the LLM. This pipeline reduces context overhead and sharpens the model's focus on relevant information. Empirical evaluation on a real-world financial transaction dataset demonstrates that RAG-FLARKO significantly enhances recommendation quality. Notably, our framework enables smaller, more efficient models to achieve high performance in both profitability and behavioral alignment, presenting a viable path for deploying grounded financial AI in resource-constrained environments.