# Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents

arXiv: https://arxiv.org/abs/2505.20368 · HTML: https://mlsanity.com/paper/2505.20368/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

## Builds on (most cited first, 20 of 20)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation](https://mlsanity.com/paper/2404.00610/) (2024)
- [LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain](https://mlsanity.com/paper/2408.10343/) (2024)
- [HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction](https://mlsanity.com/paper/2408.04948/) (2024)
- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents](https://mlsanity.com/paper/2311.09805/) (2023)
- [EfficientRAG: Efficient Retriever for Multi-Hop Question Answering](https://mlsanity.com/paper/2408.04259/) (2024)
- [SEC-QA: A Systematic Evaluation Corpus for Financial QA](https://mlsanity.com/paper/2406.14394/) (2024)

## Built on by (most cited first, 5 of 5)

- [FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering](https://mlsanity.com/paper/2508.14052/) (2025)
- [Embedding-Based Context-Aware Reranker](https://mlsanity.com/paper/2510.13329/) (2025)
- [Adaptation of Embedding Models to Financial Filings via LLM Distillation](https://mlsanity.com/paper/2512.08088/) (2025)
- [Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering](https://mlsanity.com/paper/2602.17981/) (2026)
- [Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction](https://mlsanity.com/paper/2610.19432/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) based large language models (LLMs) are widely used in finance for their excellent performance on knowledge-intensive tasks. However, standardized documents (e.g., SEC filing) share similar formats such as repetitive boilerplate texts, and similar table structures. This similarity forces traditional RAG methods to misidentify near-duplicate text, leading to duplicate retrieval that undermines accuracy and completeness. To address these issues, we propose the Hierarchical Retrieval with Evidence Curation (HiREC) framework. Our approach first performs hierarchical retrieval to reduce confusion among similar texts. It first retrieve related documents and then selects the most relevant passages from the documents. The evidence curation process removes irrelevant passages. When necessary, it automatically generates complementary queries to collect missing information. To evaluate our approach, we construct and release a Large-scale Open-domain Financial (LOFin) question answering benchmark that includes 145,897 SEC documents and 1,595 question-answer pairs. Our code and data are available at https://github.com/deep-over/LOFin-bench-HiREC.