Thank you for attending Quant Strats Europe!
Join us at Future Alpha 2026 in New York on March 31st - April 1st
Haoxue Wang
Quant MillenniumDay 2: 15 October
10:40 AM PRESO: A Context-Engineering Based Knowledge Framework for Quantitative Finance
Quantitative research increasingly relies on unstructured financial content such as filings, earnings calls, and research notes, yet existing LLM and RAG pipelines struggle with point-in-time correctness, evidence attribution, and integration into research workflows.
To tackle this, QuantMind introduces an intelligent knowledge extraction and retrieval framework tailored to quantitative finance. It adopts a two-stage architecture:
Knowledge Extraction – transforms heterogeneous documents into structured knowledge through multi-modal parsing of text, tables, and formulas; applies adaptive summarization for scalability; and uses domain-specific tagging for fine-grained indexing.
Intelligent Retrieval – integrates semantic search with flexible strategies, multi-hop reasoning across sources, and knowledge-aware generation for auditable outputs.
A controlled user study shows that QuantMind improves both factual accuracy and user experience compared to unaided reading and generic AI assistance, highlighting the value of structured, domain-specific context engineering for finance.
Check out the incredible speaker line-up to see who will be joining Haoxue.
Download The Latest Agenda
