Work

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

Year: 2025

Type: conference-paper

Abstract: 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.

DOI: 10.18653/v1/2025.findings-acl.855

Authors: Jaeyoung Choe, Jihoon Kim, Woohwan Jung

Institution: Hanyang University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funders: Ministry of Science and ICT, South Korea, Institute for Information and Communications Technology Promotion

Awards: G179064740, G189783378

OpenAlex ID: W4412888134