한국정보처리학회:학술대회논문집 (Proceedings of the Korea Information Processing Society Conference)

한국정보처리학회 (Korea Information Processing Society)
권호 표지

Enhancing Automated Report Generation: Integrating Rivet and RAG with Advanced Retrieval Techniques

  • Doo-Il Kwak (Dept. of AI Techno Convergence, Soongsil University) ;
  • Kwang-Young Park (Dept. of AI Techno Convergence, Soongsil University)
  • 발행 : 2024.05.23
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This study integrates Rivet and Retrieved Augmented Generation (RAG) technologies to enhance automated report generation, addressing the challenges of large-scale data management. We introduce novel algorithms, such as Dynamic Data Synchronization and Contextual Compression, expected to improve report generation speed by 40% and accuracy by 25%. The application, demonstrated through a model corporate entity, "Company L," shows how such integrations can enhance business intelligence. Empirical validations planned will utilize metrics like precision, recall, and BLEU to substantiate the improvements, setting new benchmarks for the industry. This research highlights the potential of advanced technologies in transforming corporate data processes.

키워드

과제정보

This work was supported by Innovative Human Resource Development for Local Intellectualization program through the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (IITP-2024-RS-2022-00156360)

참고문헌

  1. Roger S. Pressman, Bruce R. Maxim, "Software Engineering: A Practitioner's Approach", New York, NY, McGraw-Hill Education, 2020.
  2. Wu, Y., Han, Y., Shao, F., Guo, Z., "Research Personalized Learning Report Generation--An Example from a Course on Integration of Information Technology and Physics Curriculum", 2023 International Conference on Intelligent Education and Intelligent Research (IEIR), 2023, pp. 1-6.
  3. Jiang, Y. (2022) "SDW-ASL: A Dynamic System to Generate Large Scale Dataset for Continuous American Sign Language," ArXiv, abs/2210.06791, 2022.
  4. Yadav, G., Yadav, R., Viramgama, M., Viramgama, M., Mohite, A. (2024) "Quantixar: High-performance Vector Data Management System," ArXiv, abs/2403.12583, 2024.
  5. Vasireddy, P., Kavi, K., Weaver, A., Mehta, G. (2023) "Streaming Sparse Data on Architectures with Vector Extensions using Near Data Processing" , 2023, pp. 16:1-16:12.
  6. Shahmansoori, A. (2024) "Concurrent Brainstorming & Hypothesis Satisfying: An Iterative Framework for Enhanced Retrieval-Augmented Generation (R2CBR3HSR)," ArXiv, abs/2401.01835, 2024.
  7. LangChain, 'Parent Document Retriever', 2024. [Online]. Available: https://python.langchain.com/docs/modules/data_connect ion/retrievers/parent_document_retriever/ [Accessed: April 19, 2024].
  8. LangChain, 'Contextual compression', 2023. [Online]. Available: https://python.langchain.com/docs/modules/data_connection/retrievers/contextual_compression/ [Accessed: April 19, 2024].
  9. Rangan, K., Yin, Y. (2024) "A Fine-tuning Enhanced RAG System with Quantized Influence Measure as AI Judge," ArXiv, abs/2402.17081, 2024.
  10. Ironclad, 'rivet: The open-source visual AI programming environment and TypeScript library', GitHub, 2024. [Online]. Available: https://github.com/Ironclad/rivet [Accessed: April 19, 2024].
  11. SerpApi, 'Google Search API', 2024. [Online]. Available: https://serpapi.com/ [Accessed: April 19, 2024].
  12. npm, 'About npm', npm Docs, 2023. [Online]. Available: https://docs.npmjs.com/about-npm [Accessed: April 19, 2024].
  13. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Kuttler, Mike Lewis, Wen-tau Yih, Tim Rocktaschel, Sebastian Riedel, Douwe Kiela, 'Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks', arXiv.org, 2020. [Online]. Available: https://arxiv.org/abs/2005.11401 [Accessed: April 19, 2024].
  14. Damian Gil, 'Advanced Retriever Techniques to Improve Your RAGs', Towards Data Science, Medium, 2024. [Online]. Available: https://towardsdatascience.com/advanced-retrievertechniques-to-improve-your-rags-1fac2b86dd61 [Accessed: April 19, 2024].
  15. Azhar, "RAG and Parent Document Retrievers: Making Sense of Complex Contexts with Code," Medium, 2023. [Online]. Available: https://medium.com/ai-insightscobet/rag-and-parent-document-retrievers-making-senseof-complex-contexts-with-code-5bd5c3474a8a [Accessed: April 22, 2024].
  16. Azhar, 2023, retrieved from Medium on April 22, 2024
  17. Azhar, 2023, retrieved from Medium on April 22, 2024