arXiv subjects

Ines Abdeljaoued-Tej

Publications and source records attributed to Ines Abdeljaoued-Tej.

4 recordsLinked to original sources

arXiv2026

LLM-Based Code Documentation Generation and Multi-Judge Evaluation

High-quality source code documentation is vital yet often neglected, especially in critical domains like healthcare where reliability and maintainability are essential. We presented an AI powered framework that automates documentation generation from code and repositories using eight state of the art Large Language Models (LLMs), including GPT, Gemini, Qwen, and LLaMA variants. Built on the PocketFlow orchestration framework, the system applies modular pipelines and advanced prompt engineering to produce structured, context aware documentation. To ensure quality and guide model selection, we introduced a MultiLLMasJudges evaluation framework, where four independent LLMs assess outputs across nine criteria, such as Completeness, Clarity, and Faithfulness. Experiments conducted on an open-source medical physics library, demonstrated showed a 42% performance gap between top and bottom models. By combining diverse model outputs, optimized prompting, and rigorous evaluation, our approach enhances documentation quality and reduces manual effort, especially in safety critical healthcare software.

cs.HC↗

arXiv2026

Rabies diagnosis in low-data settings: A comparative study on the impact of data augmentation and transfer learning

Rabies remains a major public health concern across many African and Asian countries, where accurate diagnosis is critical for effective epidemiological surveillance. The gold standard diagnostic methods rely heavily on fluorescence microscopy, necessitating skilled laboratory personnel for the accurate interpretation of results. Such expertise is often scarce, particularly in regions with low annual sample volumes. This paper presents an automated, AI-driven diagnostic system designed to address these challenges. We developed a robust pipeline utilizing fluorescent image analysis through transfer learning with four deep learning architectures: EfficientNetB0, EfficientNetB2, VGG16, and Vision Transformer (ViTB16). Three distinct data augmentation strategies were evaluated to enhance model generalization on a dataset of 155 microscopic images (123 positive and 32 negative). Our results demonstrate that TrivialAugmentWide was the most effective augmentation technique, as it preserved critical fluorescent patterns while improving model robustness. The EfficientNetB0 model, utilizing Geometric & Color augmentation and selected through stratified 3fold cross-validation, achieved optimal classification performance on cropped images. Despite constraints posed by class imbalance and a limited dataset size, this work confirms the viability of deep learning for automating rabies diagnosis. The proposed method enables fast and reliable detection with significant potential for further optimization. An online tool was deployed to facilitate practical access, establishing a framework for future medical imaging applications. This research underscores the potential of optimized deep learning models to transform rabies diagnostics and improve public health outcomes.

cs.CV↗

arXiv2025

CAPRAG: A Large Language Model Solution for Customer Service and Automatic Reporting using Vector and Graph Retrieval-Augmented Generation

The introduction of new features and services in the banking sector often overwhelms customers, creating an opportunity for banks to enhance user experience through financial chatbots powered by large language models (LLMs). We initiated an AI agent designed to provide customers with relevant information about banking services and insights from annual reports. We proposed a hybrid Customer Analysis Pipeline Retrieval-Augmented Generation (CAPRAG) that effectively addresses both relationship-based and contextual queries, thereby improving customer engagement in the digital banking landscape. To implement this, we developed a processing pipeline to refine text data, which we utilized in two main frameworks: Vector RAG and Graph RAG. This dual approach enables us to populate both vector and graph databases with processed data for efficient retrieval. The Cypher query component is employed to effectively query the graph database. When a user submits a query, it is first expanded by a query expansion module before being routed to construct a final query from the hybrid Knowledge Base (KB). This final query is then sent to an open-source LLM for response generation. Overall, our innovative, designed to international banks, serves bank's customers in an increasingly complex digital environment, enhancing clarity and accessibility of information.

cs.CL↗

arXiv2018

A linear algorithm for computing Polynomial Dynamical System

Computation biology helps to understand all processes in organisms from interaction of molecules to complex functions of whole organs. Therefore, there is a need for mathematical methods and models that deliver logical explanations in a reasonable time. For the last few years there has been a growing interest in biological theory connected to finite fields: the algebraic modeling tools used up to now are based on Gröbner bases or Boolean group. Let $n$ variables representing gene products, changing over the time on $p$ values. A Polynomial dynamical system (PDS) is a function which has several components, each one is a polynom with $n$ variables and coefficient in the finite field $Z/pZ$ that model the evolution of gene products. We propose herein a method using algebraic separators, which are special polynomials abundantly studied in effective Galois theory. This approach avoids heavy calculations and provides a first Polynomial model in linear time.

q-bio.MN↗