{"ID":2859023,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.11583","arxiv_id":"2511.11583","title":"Parallel and Multi-Stage Knowledge Graph Retrieval for Behaviorally Aligned Financial Asset Recommendations","abstract":"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.","short_abstract":"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 in...","url_abs":"https://arxiv.org/abs/2511.11583","url_pdf":"https://arxiv.org/pdf/2511.11583v1","authors":"[\"Fernando Spadea\",\"Oshani Seneviratne\"]","published":"2025-10-08T20:42:53Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.IR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}