Retrieval Augmented Generation for Question Answering in Financial Documents

Year : 2025 | Volume : 12 | Issue : 02 | Page : 62 68
    By

    S. Sharon Benita,

  • V. Srividhya,

  1. Student, Master of Computer Applications, Avinashilingam Institute for Home Science and Higher Education for Women, Coimbatore, Tamil Nadu, India
  2. Associate Professor, Department of Computer Science, Avinashilingam Institute for Home Science and Higher Education for Women, Coimbatore, Tamil Nadu, India

Abstract

In recent years, the integration of Question Answering (QA) with the Retrieval Augmented Generation (RAG) system has transformed to interact with numerous documents. It uses Natural Language Processing (NLP) techniques to improve accuracy and relevant responses derived from huge documents. RAG integrates the advantages of the retrieval and generation process, which allows systems to generate natural responses and extract context from multiple sources. The main reason to use RAG is that it can help Large Language Model (LLM). Several personalized pieces of information are used in the RAG architecture. In this work, the financial domain is used to handle the financial documents to answer complex questions that efficiently retrieve knowledge of specific terms and context to generate the answers. Collections of financial documents are used to create questions with answers based on the information provided and to compare the performance of the system with known ground truth answers. The ROUGE score is used to evaluate the performance of the RAG. It is used to evaluate the accuracy between the generated responses and matched reference answers for a range of questions. Finally, incorporating RAG into question answering frameworks can improve user interface, confidence, and accuracy in automated solutions in the finance domain.

Keywords: Retrieval augmented generation, natural language processing, embedding, large language model, ROUGE score

[This article belongs to Journal of Advanced Database Management & Systems ]

How to cite this article:
S. Sharon Benita, V. Srividhya. Retrieval Augmented Generation for Question Answering in Financial Documents. Journal of Advanced Database Management & Systems. 2025; 12(02):62-68.
How to cite this URL:
S. Sharon Benita, V. Srividhya. Retrieval Augmented Generation for Question Answering in Financial Documents. Journal of Advanced Database Management & Systems. 2025; 12(02):62-68. Available from: https://journals.stmjournals.com/joadms/article=2025/view=226214


References

  1. Biancofiore GM, Deldjoo Y, Noia TD, Di Sciascio E, Narducci F. Interactive question answering systems: Literature review. ACM Comput Surv. 2024 May 8; 56(9): 1–38.
  2. Usbeck R, Röder M, Hoffmann M, Conrads F, Huthmann J, Ngonga-Ngomo AC, Demmler C, Unger C. Benchmarking question answering systems. Semant Web. 2019 Jan 21; 10(2): 293–304.
  3. Nassiri K, Akhloufi M. Transformer models used for text-based question answering systems. Appl Intell. 2023 May; 53(9): 10602–35.
  4. Abbasiantaeb Z, Momtazi S. Text‐based question answering from information retrieval and deep neural network perspectives: A survey. Wiley Interdiscip Rev: Data Min Knowl Discov. 2021 Nov; 11(6): e1412.
  5. Jayakumar H, Krishnakumar MS, Peddagopu VV, Sridhar R. RNN based question answer generation and ranking for financial documents using financial NER. Sādhanā. 2020 Dec; 45: 269.
  6. Phogat KS, Puranam SA, Dasaratha S, Harsha C, Ramakrishna S. Fine-tuning Smaller Language Models for Question Answering over Financial Documents. arXiv preprint arXiv:2408.12337. 2024 Aug 22.
  7. Shah S, Ryali S, Venkatesh R. Multi-Document Financial Question Answering using LLMs. arXiv preprint arXiv:2411.07264. 2024 Nov 8.
  8. Srivastava P, Malik M, Gupta V, Ganu T, Roth D. Evaluating LLMs’ Mathematical Reasoning in Financial Document Question Answering. arXiv preprint arXiv:2402.11194. 2024 Feb 17.
  9. Singh K, Kaur S, Smiley C. FinQAPT: Empowering Financial Decisions with End-to-End LLM-driven Question Answering Pipeline. In Proceedings of the 5th ACM International Conference on AI in Finance. 2024 Nov 14; 266–273.
  10. Hugging Face. (2025). Hugging Face – The AI community building the future. [online] Hugging Face. Available from: https://huggingface.co/
  11. Wang L, Yang N, Huang X, Yang L, Majumder R, Wei F. Improving text embeddings with large language models. arXiv preprint arXiv:2401.00368. 2023 Dec 31.
  12. Kukreja S, Kumar T, Purohit A, Dasgupta A, Guha D. A literature survey on open source large language models. In Proceedings of the 2024 7th International Conference on Computers in Management and Business. 2024 Jan 12; 133–143.
  13. Chen A, Stanovsky G, Singh S, Gardner M. Evaluating question answering evaluation. In Proceedings of the 2nd workshop on machine reading for question answering. 2019 Nov; 119–124.
Regular Issue Subscription Review Article
Volume 12
Issue 02
Received 28/04/2025
Accepted 20/06/2025
Published 27/09/2025
Publication Time 152 Days
230

Login


My IP

PlumX Metrics