VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912644222418944 |
|---|---|
| author | Tai, Zhenghan Wu, Hanwei Hu, Qingchen Chi, Jijun He, Hailin Ding, Lei Kwok, Tung Sum Thomas Xiao, Bohuai Hua, Yuchen Wang, Suyuchen Lu, Peng Li, Muzhi Wu, Yihong Ma, Liheng Huang, Jerry Zhang, Jiayi Zhang, Gonghao Jiang, Chaolong Tian, Jingrui Lyu, Sicheng Li, Zeyu Han, Boyu Mo, Fengran Yu, Xinyue Cui, Yufei Zhou, Ling Wang, Xinyu |
| author_facet | Tai, Zhenghan Wu, Hanwei Hu, Qingchen Chi, Jijun He, Hailin Ding, Lei Kwok, Tung Sum Thomas Xiao, Bohuai Hua, Yuchen Wang, Suyuchen Lu, Peng Li, Muzhi Wu, Yihong Ma, Liheng Huang, Jerry Zhang, Jiayi Zhang, Gonghao Jiang, Chaolong Tian, Jingrui Lyu, Sicheng Li, Zeyu Han, Boyu Mo, Fengran Yu, Xinyue Cui, Yufei Zhou, Ling Wang, Xinyu |
| contents | Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from complex public disclosures are crucial. However, existing financial RAG systems face two significant challenges: (1) they struggle to process heterogeneous data formats, such as text, tables, and figures; and (2) they encounter difficulties in balancing general-domain applicability with company-specific adaptation. To overcome these challenges, we present VeritasFi, an innovative hybrid RAG framework that incorporates a multi-modal preprocessing pipeline alongside a cutting-edge two-stage training strategy for its re-ranking component. VeritasFi enhances financial QA through three key innovations: (1) A multi-modal preprocessing pipeline that seamlessly transforms heterogeneous data into a coherent, machine-readable format. (2) A tripartite hybrid retrieval engine that operates in parallel, combining deep multi-path retrieval over a semantically indexed document corpus, real-time data acquisition through tool utilization, and an expert-curated memory bank for high-frequency questions, ensuring comprehensive scope, accuracy, and efficiency. (3) A two-stage training strategy for the document re-ranker, which initially constructs a general, domain-specific model using anonymized data, followed by rapid fine-tuning on company-specific data for targeted applications. By integrating our proposed designs, VeritasFi presents a groundbreaking framework that greatly enhances the adaptability and robustness of financial RAG systems, providing a scalable solution for both general-domain and company-specific QA tasks. Code accompanying this work is available at https://github.com/simplew4y/VeritasFi.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10828 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering Tai, Zhenghan Wu, Hanwei Hu, Qingchen Chi, Jijun He, Hailin Ding, Lei Kwok, Tung Sum Thomas Xiao, Bohuai Hua, Yuchen Wang, Suyuchen Lu, Peng Li, Muzhi Wu, Yihong Ma, Liheng Huang, Jerry Zhang, Jiayi Zhang, Gonghao Jiang, Chaolong Tian, Jingrui Lyu, Sicheng Li, Zeyu Han, Boyu Mo, Fengran Yu, Xinyue Cui, Yufei Zhou, Ling Wang, Xinyu Information Retrieval Artificial Intelligence Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from complex public disclosures are crucial. However, existing financial RAG systems face two significant challenges: (1) they struggle to process heterogeneous data formats, such as text, tables, and figures; and (2) they encounter difficulties in balancing general-domain applicability with company-specific adaptation. To overcome these challenges, we present VeritasFi, an innovative hybrid RAG framework that incorporates a multi-modal preprocessing pipeline alongside a cutting-edge two-stage training strategy for its re-ranking component. VeritasFi enhances financial QA through three key innovations: (1) A multi-modal preprocessing pipeline that seamlessly transforms heterogeneous data into a coherent, machine-readable format. (2) A tripartite hybrid retrieval engine that operates in parallel, combining deep multi-path retrieval over a semantically indexed document corpus, real-time data acquisition through tool utilization, and an expert-curated memory bank for high-frequency questions, ensuring comprehensive scope, accuracy, and efficiency. (3) A two-stage training strategy for the document re-ranker, which initially constructs a general, domain-specific model using anonymized data, followed by rapid fine-tuning on company-specific data for targeted applications. By integrating our proposed designs, VeritasFi presents a groundbreaking framework that greatly enhances the adaptability and robustness of financial RAG systems, providing a scalable solution for both general-domain and company-specific QA tasks. Code accompanying this work is available at https://github.com/simplew4y/VeritasFi.git. |
| title | VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10828 |