PEARL: Provenance-aware Evidence-grounded Adaptive Retrieval Layer

Nagoor, Shreyas; Anand, Bhaskar; Satpathy, Ayush; R, Anitha; Kuzhalvaimozhi, S.

doi:https://doi.org/10.55041/ijcope.v2i5.643

Volume 02, Issue 05

Published on: May 2026

PEARL: PROVENANCE-AWARE EVIDENCE-GROUNDED ADAPTIVE RETRIEVAL LAYER

Shreyas Nagoor Bhaskar Anand Ayush Satpathy Anitha R S. Kuzhalvaimozhi

DOI:https://doi.org/10.55041/ijcope.v2i5.643

Article Status

Plagiarism Passed Peer Reviewed Open Access

Available Documents

Download PDF Review Report

Abstract

Access to information embedded within large-scale, multilingual government and policy documents remains a criti-cal challenge in low-resource computational environments. This paper presents a Provenance-Aware Multilingual Retrieval-Augmented Generation framework designed for real-time ques-tion answering over long, heterogeneous document collections. The proposed system integrates automated language identifica-tion and bidirectional machine translation within a semantic retrieval pipeline, enabling context-preserving access to docu-ments spanning multiple languages and domains, including legal and policy terminology. By leveraging Sentence Transformer embeddings, FAISS-based vector indexing, and a provenance-grounded generative component, the framework delivers ac-curate, evidence-backed responses without reliance on GPU acceleration. Comprehensive evaluations confirm that the system achieves high extraction fidelity, retrieval relevance, and genera-tive accuracy, with an average end-to-end response latency of 2.1 seconds on standard CPU hardware. Results further demonstrate that the framework consistently outperforms baseline retrieval and generation systems in both multilingual robustness and usability, establishing it as a scalable and deployable solution for document intelligence in resource-constrained settings.

Index Terms—Retrieval-Augmented Generation, Multilingual Question Answering, Semantic Retrieval, Large Language Mod-els, Document Intelligence

How to Cite this Paper

Nagoor, S., Anand, B., Satpathy, A., R, A. & Kuzhalvaimozhi, S. (2026). PEARL: Provenance-aware Evidence-grounded Adaptive Retrieval Layer. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(05). https://doi.org/10.55041/ijcope.v2i5.643

Nagoor, Shreyas, et al.. "PEARL: Provenance-aware Evidence-grounded Adaptive Retrieval Layer." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 05, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i5.643.

Nagoor, Shreyas,Bhaskar Anand,Ayush Satpathy,Anitha R, and S. Kuzhalvaimozhi. "PEARL: Provenance-aware Evidence-grounded Adaptive Retrieval Layer." International Journal of Creative and Open Research in Engineering and Management 02, no. 05 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i5.643.

Search & Index

References

Robertson and H. Zaragoza, “The probabilistic relevance framework: BM25 and beyond,” Foundations and Trends in Information Retrieval, vol. 3, no. 4, pp. 333–389, 2009.

Ji, N. Lee, R. Frieske, T. Yu, D. Su, Y. Xu, E. Ishii, Y. J. Bang,Madotto, and P. Fung, “Survey of hallucination in natural language generation,” ACM Computing Surveys, 2023.

Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal,Ku¨ttler, M. Lewis, W.-t. Yih, T. Rockta¨schel, S. Riedel, and D. Kiela, “Retrieval-augmented generation for knowledge-intensive NLP tasks,” in Advances in Neural Information Processing Systems, 2020.

Sharma, K. Patel, and A. Kumar, “Multilingual information systems: Challenges and solutions,” Journal of Information Systems Research, 2023.

Conneau, K. Khandelwal, N. Goyal, V. Chaudhary, G. Wenzek,Guzma´n, E. Grave, M. Ott, L. Zettlemoyer, and V. Stoyanov, “Unsu-pervised cross-lingual representation learning at scale,” in Proceedings of ACL, 2020.

Karpukhin, B. Oguz, S. Min, P. Lewis, L. Wu, S. Edunov, D. Chen, and W.-t. Yih, “Dense passage retrieval for open-domain question answering,” in Proceedings of EMNLP, 2020.

Reimers and I. Gurevych, “Sentence-BERT: Sentence embeddings using siamese BERT-networks,” in Proceedings of EMNLP, 2019.

Johnson, M. Douze, and H. Je´gou, “Billion-scale similarity search with GPUs,” IEEE Transactions on Big Data, 2019.

Zhang, Q. Wang, and Y. Liu, “Document chunking strategies for large-scale information retrieval,” in Proceedings of EMNLP, 2022.

Gupta, P. Singh, and S. Verma, “Ai-powered domain-specific assis-tants: A systematic review of deployment strategies,” AI Applications Review, 2023.

Chen, M. Rodriguez, and K. Johnson, “Evaluation frameworks for conversational AI in domain-specific applications,” Transactions on Interactive Intelligent Systems, 2023.

Ethical Compliance & Review Process

•All submissions are screened under plagiarism detection.
•Review follows editorial policy.
•Authors retain copyright.
•Peer Review Type: Double-Blind Peer Review
•Published on: May 21 2026

CCBYNC

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.

View License

Back to Volume 02, Issue 05 View All Issues Next Article

← Previous Article

Parametric Analysis of Welding Processes and Their influence on Joint Strength

Next Article →

Perceived Organizational Support on Turnover Intention Mediating by Perceived Value of Artificial Intelligence and Transformational Leadership