We use a few cookies

Essential cookies keep the library working. With your permission, we'd also like to use analytics to see what's useful and improve the experience. Read our Privacy Policy or Cookie Policy.

Skip to main content
Home/e-Resources/Cyber Security/Attention Mapping for Hallucination Reduction in Arabic Financial Using Retrieval-Augmented Generation Systems
PeriodicalsCyber Security

Attention Mapping for Hallucination Reduction in Arabic Financial Using Retrieval-Augmented Generation Systems

Checking your access to this record.

Abstract & Overview

This research introduces a customized attention visualization framework for mitigating hallucinations in Arabic Retrieval-Augmented Generation (RAG) systems tailored for financial document analysis. The proposed architecture extends MarBERT with a dual-stage attention supervision mechanism and a hallucination-aware loss formulation, trained on a newly constructed dataset of 7,000 annotated Arabic financial query-context pairs. A grounding alignment score is computed over attended tokens, and generated responses are rejected when falling below a dynamically adjusted precision-aware threshold,serving as the core decision-making approach for hallucination detection. The system achieves 95.04% classification accuracy, 95.84% precision, 94.12% recall, and an F1 score of 94.97%, outperforming AraELECTRA and mBERT-RAG baselines. For hallucination detection, it reaches an 87.63% detection rate with only 8.91% false alarms and a detection latency of 3.2 tokens, showcasing reliability in identifying ungrounded financial claims. Visualizations using cross-attention matrices and token contribution scores reveal consistent alignment with critical Arabic financial terms, temporal expressions, and entity references. An interactive attention interface further empowers non-technical users to identify hallucinations with 83.4% success in usability tests. These results validate the effectiveness of integrating interpretable attention modeling with domain-specific retrieval, offering a scalable approach for risk-sensitive natural language processing in low-resource languages.

Cite this record

Hasan A. Hasan, Khaldoun H. Al-Hussayni, Ali Z. K. Matloob (2025). Attention Mapping for Hallucination Reduction in Arabic Financial Using Retrieval-Augmented Generation Systems. Journal of Intelligent Informatics Networking and Cybersecurity, 1(2). https://doi.org/10.65445/3106-1192.1006

Copy in another style

Hasan, H. A., Al-Hussayni, K. H., & Matloob, A. Z. K. (2025). Attention Mapping for Hallucination Reduction in Arabic Financial Using Retrieval-Augmented Generation Systems. Journal of Intelligent Informatics Networking and Cybersecurity, 1(2). https://doi.org/10.65445/3106-1192.1006
Author names are used as deposited, so check their order before you submit.

Metadata is harvested from open-access indexes and can be incomplete. Check a citation against the published version before relying on it — see our open access & attribution policy.