Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal The Eastasouth Journal of Information System and Computer Science
Varsha Shah
Independent Researcher, Seattle, WA, USA
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Context-Aware Document Intelligence for Automated Compliance Evidence Extraction from Heterogeneous Financial Documents Varsha Shah
The Eastasouth Journal of Information System and Computer Science Vol. 1 No. 01 (2023): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v1i01.1222

Abstract

Regulatory compliance activities across the financial sector produce a vast and growing amount of unstructured evidentiary material, such as loan agreements, non-disclosure agreements, annual reports, disclosure forms, scanned correspondence, and more — all of which auditors and regulators must review to assure compliance with disclosure, anti-money-laundering and data-protection requirements. Text-only Natural Language Processing pipelines are unable to handle this type of content because the facts relevant to compliance are often embedded in the format of a page, such as signature blocks, tabular disclosures and heading to clauses. This paper summarizes the results of two and a half years of work, including twenty-five papers from the field of transformer language modeling, the field of layout-aware document representation learning, the field of financial natural language processing and the field of applied regulatory-technology systems, all of which were published between 2015 and 2022. It explores how the performance of text-only encoders jumped from an F1 score of around sixty percent on benchmarks for form understanding to the layout-aware multimodal architectures that exceeded the ninety percent mark on the same benchmark, and reviews applied systems that lowered the manual anti-money-laundering review workload by more than fifty percent while maintaining detection rates above eighty percent. The review also outlines five benchmark datasets that test extraction tasks that are related to compliance and suggests a generalized six-stage extraction pipeline extracted from the reviewed architectures. The results show that layout-conditioned pretraining yields the highest improvements, not just a parameter scale, and that the human verification is a constant characteristic of all the deployed systems studied.
Failure-to-Risk: Predicting Compliance Breaches from Process Anomalies Using Temporal Explainable AI Varsha Shah
The Eastasouth Journal of Information System and Computer Science Vol. 1 No. 03 (2024): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v1i03.1224

Abstract

Non-conformances in organizational processes are often observed as slight irregularities in the sequence of events, prior to even the formal event of a non-conformance being reported, leading to an increased interest in predictive models that can detect such irregularities and give a reason for each alert. This review summarizes the methodological progress of predictive business process monitoring, temporal deep learning and explainable AI and proposes an overall conceptual framework, called temporal explainable AI for compliance-risk prediction, which brings together sequence encoders (e.g. LSTM networks, attention-based transformers) and explainers for post-hoc interpretation (e.g. Shapley additive explanations, local surrogate models, rule-based anchors). The synthesis moves from classical models of stochastic processes to data-driven temporal architectures, laying out the corresponding loss of native interpretability for predictive flexibility, and describing how post-hoc explanation methods have been devised to reclaim the lost interpretability. The results of a comparative review of benchmark evaluations on predictive process monitoring also show that key aspects of the evaluations that are relevant to predictive process monitoring, such as the encoding strategy, cross-log generalization, or handling of class imbalance, have a significant impact on the reported performance and should be taken into account when designing a deployed compliance-risk system. A comprehensive temporal explainable AI system for compliance monitoring should also include concept-drift detection, as the statistical correlation between process behavior and compliance outcomes will not likely be constant throughout an organization's lifecycle.
GovernedRAG: Risk-Adaptive Retrieval-Augmented Generation for Enterprise Compliance Decision Support Varsha Shah
The Eastasouth Journal of Information System and Computer Science Vol. 2 No. 03 (2025): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v2i03.1229

Abstract

When enterprises rely on LLMs for compliance decision support because they are under sustained regulatory scrutiny, retrieval-augmented generation without control allows access-sensitive regulatory, contractual, and audit content to be surfaced indiscriminately, and it does not tailor its response to the risk level of the query. This paper combines the latest research in retrieval-augmented generation, access control, adversarial threats, and AI risk management and introduces GovernedRAG, an architecture for enterprise compliance decision support that adapts to risk. The architecture integrates a four-stage risk classifier, a retrieval gate that limits the scope of candidate evidence retrieved to the scope of the requesting user before they are ranked, a grounded generation stage with an evaluation loop based on the reference-free assessment frameworks, and a continuous evaluation loop. A formalization is provided for the risk-weighted relevance, access gating, and faithfulness scoring, and the proposal is compared to five related retrieval-augmented paradigms, and the proposal is juxtaposed with them. It shows that governance and risk adaptivity are still not considered as first-class architectural concerns in previous retrieval-augmented systems, that access control is still mostly outside of retrieval ranking and not embedded in the ranking function, and that reference-free evaluation protocols are practical foundations for ongoing, compliance-driven monitoring. The proposed framework is organized into four risk tiers, four architectural stages and six comparative synthesis tables. Consequences for auditing, regulation and empirical confirmation are considered.
Co-Authors