QuantMind: A Context-Engineering Based Knowledge Framework for Quantitative Finance

2025/09/25 by Wang, Haoxue, Wen, Keli, Li, Yuante +11
#Computational Engineering #FOS: Computer and information sciences #Finance #and Science (cs.CE)

paper · doi:10.48550/arxiv.2509.21507

Abstract

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, We present QuantMind, an intelligent knowledge extraction and retrieval framework tailored to quantitative finance. QuantMind adopts a two-stage architecture: (i) a knowledge extraction stage that transforms heterogeneous documents into structured knowledge through multi-modal parsing of text, tables, and formulas, adaptive summarization for scalability, and domain-specific tagging for fine-grained indexing; and (ii) an intelligent retrieval stage that integrates semantic search with flexible strategies, multi-hop reasoning across sources, and knowledge-aware generation for auditable outputs. A controlled user study demonstrates that QuantMind improves both factual accuracy and user experience compared to unaided reading and generic AI assistance, underscoring the value of structured, domain-specific context engineering for finance.

Citations

• A Survey of Context Engineering for Large Language Models
• Replication of Reference-Dependent Preferences and the Risk-Return Trade-Off in the Chinese Market
• Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction
• Panel Data Nowcasting: The Case of Price-Earnings Ratios
• FinGPT: Open-Source Financial Large Language Models
• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
• BloombergGPT: A Large Language Model for Finance
• GPT-4 Technical Report
• OpenAlex Snapshot
• ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
• Dense Passage Retrieval for Open-Domain Question Answering
• Answering Complex Open-domain Questions Through Iterative Query Generation
• FinBERT: Financial Sentiment Analysis with Pre-trained Language Models
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Passage Re-ranking with BERT
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Reading Wikipedia to Answer Open-Domain Questions
• The Pricing of Options and Corporate Liabilities

Related

• QuantMCP: Grounding Large Language Models in Verifiable Financial Reality
• Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction
• Financial Knowledge Large Language Model
• QuantBench: Benchmarking AI Methods for Quantitative Investment
• RAG-IT: Retrieval-Augmented Instruction Tuning for Automated Financial Analysis -- A Case Study for the Semiconductor Sector