FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval
Preprint
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.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- LightRAG: Simple and Fast Retrieval-Augmented Generation2025
- INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent2025
- Lost in the Middle: How Language Models Use Long ContextsTransactions of the Association for Computational Linguistics, 2024
- RAGAs: Automated Evaluation of Retrieval Augmented Generation2024
- Modeling News Interactions and Influence for Financial Market Prediction2024
- Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity2024
- Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models2023
- Longtriever: a Pre-trained Long Text Encoder for Dense Document Retrieval2023
- FinQA: A Dataset of Numerical Reasoning over Financial Data2021
- On Faithfulness and Factuality in Abstractive Summarization2020