FinSage: A Multi-aspect RAG System for Financial Filings Question Answering
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913990061326336 |
|---|---|
| author | Wang, Xinyu Chi, Jijun Tai, Zhenghan Kwok, Tung Sum Thomas Li, Muzhi Li, Zhuhong He, Hailin Hua, Yuchen Lu, Peng Wang, Suyuchen Wu, Yihong Huang, Jerry Tian, Jingrui Mo, Fengran Cui, Yufei Zhou, Ling |
| author_facet | Wang, Xinyu Chi, Jijun Tai, Zhenghan Kwok, Tung Sum Thomas Li, Muzhi Li, Zhuhong He, Hailin Hua, Yuchen Lu, Peng Wang, Suyuchen Wu, Yihong Huang, Jerry Tian, Jingrui Mo, Fengran Cui, Yufei Zhou, Ling |
| contents | Leveraging large language models in real-world settings often entails a need to utilize domain-specific data and tools in order to follow the complex regulations that need to be followed for acceptable use. Within financial sectors, modern enterprises increasingly rely on Retrieval-Augmented Generation (RAG) systems to address complex compliance requirements in financial document workflows. However, existing solutions struggle to account for the inherent heterogeneity of data (e.g., text, tables, diagrams) and evolving nature of regulatory standards used in financial filings, leading to compromised accuracy in critical information extraction. We propose the FinSage framework as a solution, utilizing a multi-aspect RAG framework tailored for regulatory compliance analysis in multi-modal financial documents. FinSage introduces three innovative components: (1) a multi-modal pre-processing pipeline that unifies diverse data formats and generates chunk-level metadata summaries, (2) a multi-path sparse-dense retrieval system augmented with query expansion (HyDE) and metadata-aware semantic search, and (3) a domain-specialized re-ranking module fine-tuned via Direct Preference Optimization (DPO) to prioritize compliance-critical content. Extensive experiments demonstrate that FinSage achieves an impressive recall of 92.51% on 75 expert-curated questions derived from surpasses the best baseline method on the FinanceBench question answering datasets by 24.06% in accuracy. Moreover, FinSage has been successfully deployed as financial question-answering agent in online meetings, where it has already served more than 1,200 people. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14493 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FinSage: A Multi-aspect RAG System for Financial Filings Question Answering Wang, Xinyu Chi, Jijun Tai, Zhenghan Kwok, Tung Sum Thomas Li, Muzhi Li, Zhuhong He, Hailin Hua, Yuchen Lu, Peng Wang, Suyuchen Wu, Yihong Huang, Jerry Tian, Jingrui Mo, Fengran Cui, Yufei Zhou, Ling Information Retrieval Artificial Intelligence Machine Learning Leveraging large language models in real-world settings often entails a need to utilize domain-specific data and tools in order to follow the complex regulations that need to be followed for acceptable use. Within financial sectors, modern enterprises increasingly rely on Retrieval-Augmented Generation (RAG) systems to address complex compliance requirements in financial document workflows. However, existing solutions struggle to account for the inherent heterogeneity of data (e.g., text, tables, diagrams) and evolving nature of regulatory standards used in financial filings, leading to compromised accuracy in critical information extraction. We propose the FinSage framework as a solution, utilizing a multi-aspect RAG framework tailored for regulatory compliance analysis in multi-modal financial documents. FinSage introduces three innovative components: (1) a multi-modal pre-processing pipeline that unifies diverse data formats and generates chunk-level metadata summaries, (2) a multi-path sparse-dense retrieval system augmented with query expansion (HyDE) and metadata-aware semantic search, and (3) a domain-specialized re-ranking module fine-tuned via Direct Preference Optimization (DPO) to prioritize compliance-critical content. Extensive experiments demonstrate that FinSage achieves an impressive recall of 92.51% on 75 expert-curated questions derived from surpasses the best baseline method on the FinanceBench question answering datasets by 24.06% in accuracy. Moreover, FinSage has been successfully deployed as financial question-answering agent in online meetings, where it has already served more than 1,200 people. |
| title | FinSage: A Multi-aspect RAG System for Financial Filings Question Answering |
| topic | Information Retrieval Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.14493 |