FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval

2025-09-15

AI Summary

Standard RAG exhibits low retrieval accuracy on lengthy, hierarchically structured, and terminology-dense financial disclosure documents (e.g., 10-K filings). To address this, we propose FinGEAR—the first fine-grained, query-aware retrieval framework tailored for financial documents. Methodologically, FinGEAR integrates a domain-enhanced lexicon (FLAM) with a dual-layer index structure (summary tree + question tree) to explicitly model regulatory section hierarchies and semantic relationships. It further employs a two-stage cross-encoder re-ranking mechanism to strengthen query–passage semantic alignment. Experiments on full 10-K documents demonstrate that FinGEAR improves F1 score by 56.7% over flat RAG baselines and significantly boosts downstream question answering accuracy. By enabling precise, interpretable, and robust retrieval, FinGEAR establishes a foundational advancement for high-stakes financial analysis.

Technology Category

• Natural Language Processing: Question Answering
• Data Mining & Knowledge Management: Intelligent Query Processing
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Financial disclosures such as 10-K filings present challenging retrieval problems due to their length, regulatory section hierarchy, and domain-specific language, which standard retrieval-augmented generation (RAG) models underuse. We introduce FinGEAR (Financial Mapping-Guided Enhanced Answer Retrieval), a retrieval framework tailored to financial documents. FinGEAR combines a finance lexicon for Item-level guidance (FLAM), dual hierarchical indices for within-Item search (Summary Tree and Question Tree), and a two-stage cross-encoder reranker. This design aligns retrieval with disclosure structure and terminology, enabling fine-grained, query-aware context selection. Evaluated on full 10-Ks with queries aligned to the FinQA dataset, FinGEAR delivers consistent gains in precision, recall, F1, and relevancy, improving F1 by up to 56.7% over flat RAG, 12.5% over graph-based RAGs, and 217.6% over prior tree-based systems, while also increasing downstream answer accuracy with a fixed reader. By jointly modeling section hierarchy and domain lexicon signals, FinGEAR improves retrieval fidelity and provides a practical foundation for high-stakes financial analysis.

Problem

• Retrieving precise answers from lengthy financial disclosures
• Overcoming domain-specific language challenges in financial documents
• Enhancing retrieval accuracy using hierarchical structure and finance lexicon

Innovation

• Finance lexicon guidance for retrieval
• Dual hierarchical indices for search
• Two-stage cross-encoder reranker system