Extract-Transform-Load (ETL) processes are essential for modern data-driven enterprises, enabling strategic business decision-making by integrating heterogeneous data sources into decision-support information systems. The reliability of ETL pipelines hinges on semantically correct schema matching between source schemas and the ETL-defined target schema. However, this task is complicated by schema heterogeneity and limited data access due to confidentiality constraints. Although many systems now leverage machine learning and large language models (LLMs), they still largely rely on manual intervention and large amounts of labeled data, resulting in low accuracy and limited adaptability to sensitive contexts. This paper proposes “E-AGMatch”, an automated hybrid schema matching approach powered by an open-source LLM. Its reasoning is guided by an agentic prompt built through advanced prompt engineering techniques and anchored with deterministic tools for scoring, voting, and verification. This design enables proactive schema correspondence generation while mitigating the typical LLM stochastic variability and ensuring result validation. A prototype evaluated on Purchase Order schema metadata showed promising performance, enhancing automation and reducing the requirement to access data.
Ahlem Ben Younes, Chaima Kachroud, Laila Ben Ayed et al.· Annual International Compute...· 0 citations
The exponential growth of biomedical regulatory documentation has created an urgent need for automated, scalable knowledge structuring mechanisms that do not rely on rigid, expert-curated ontologies. This paper presents the system implementation and empirical analysis of the Ontology-Free Biomedical Knowledge Graph Induction (OF-Bio-KG) framework, focusing on three dimensions: (i) the end-to-end computational pipeline, (ii) the structural and statistical properties of the induced knowledge graph, and (iii) a proposed crowd-sourced expert evaluation strategy intended for future deployment. The OF-Bio-KG framework operates on a corpus of 1,068 European Medicines Agency (EMA) pharmaceutical product leaflets totalling over 131 million tokens. Using the nomic-embed-text model for long-context semantic encoding, a Balanced K-Means Constrained clustering algorithm for thematic organization, and LLaMA-3 8B for ontology-free relational inference, the system produces a multi-level knowledge graph comprising 256,148 leaf nodes, 3,742 cluster-level concept nodes, over 1.6 million intra-cluster edges, and 147,000 inter-cluster edges, all persisted in Neo4j. A central challenge in this work is the absence of a groundtruth biomedical knowledge graph against which the induced graph can be evaluated using standard metrics. To address this, we propose a human-in-the-loop validation strategy planned for future deployment: a purpose-built web application will be made available to Master's students at ENSIT, who will act as domain-proficient annotators to explore and validate graph components. This paper describes the current system, its empirical results, and the design of this forthcoming evaluation platform.
Ahlem Ben Younes, Baha Eddine Kalai, Laila Ben Ayed et al.· Annual International Compute...· 0 citations
Adapting large language models (LLMs) to new domains using techniques like pre-training or fine-tuning can be computationally intensive. This challenge has motivated researchers and practitioners to explore alternative strategies, such as Retrieval-based augmentation mechanisms, to reduce training cost while preserving model adaptability. These mechanisms enable LLMs to generate responses grounded in external and previously unseen data. Among these approaches, RetrievalAugmented Generation (RAG) is the widely adopted due to its relatively low computational overhead. However, conventional RAG pipelines exhibit some limitations, including weak semantic coherence across retrieved contexts, limited structural reasoning capability, and the absence of explicit relational representations. To overcome these limitations, recent research has shifted toward the integration of Knowledge Graphs (KGs), which provide structured semantic representations and explicit relational modeling. KG-based approaches looks promising but the typically depend on manually designed ontologies, resulting in scalability constraints and domain adaptation challenges. To address these limitations, we propose OF-BIO-KG, a framework for automated, ontology-free knowledge graph construction. Our approach begins by projecting domain data into a vector database to identify semantically coherent clusters. An LLM then labels these clusters as conceptual nodes and infers both hierarchical and cross-cluster relationships. These nodes and links are persisted in a graph database. By eliminating the need for predefined schemas, our framework offers a scalable, computationally efficient solution for domain-specific LLM adaptation.
Ahlem Ben Younes, Baha Eddine Kalai, Laila Ben Ayed et al.· Annual International Compute...· 0 citations