Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Amamou, H.; Gagnon, S.; Davoust, A.; Avila, A. R.
Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis Proceedings Article
In: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern., pp. 80–85, Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 1062922X (ISSN); 979-833153358-8 (ISBN), (Journal Abbreviation: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.).
Abstract | Links | BibTeX | Tags: Benchmarking, Comparative analyzes, External sources, Generation systems, Information integration, Information retrieval, Knowledge graph, Knowledge graphs, Language model, Model response, Noise robustness, Pre-training, Prior-knowledge
@inproceedings{amamouRobustRetrievalAugmentedGeneration2025,
title = {Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis},
author = {H. Amamou and S. Gagnon and A. Davoust and A. R. Avila},
url = {https://www.scopus.com/pages/publications/105033145604?origin=resultslist},
doi = {10.1109/SMC58881.2025.11343466},
isbn = {1062922X (ISSN); 979-833153358-8 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
pages = {80–85},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Retrieval-Augmented Generation (RAG) was first introduced to enhance the capabilities of Large Language Models (LLMs) beyond their encoded-prior knowledge. This is achieved by providing LLMs with an external source of knowledge, which helps to reduce factual hallucinations and enables the access to new information, typically not available during their pretraining phase. Despite its benefits, there is an increasing concern with the impact of inconsistent retrieved information towards LLMs' responses. Hence, the Retrieval-Augmented Generation Benchmark (RGB) was introduced as a new testbed for RAG evaluation, meant to assess the robustness of LLMs towards inconsistency in the retrieved information. In this work, we use the RGB corpus to evaluate LLMs in four scenarios: (1) noise robustness; (2) information integration; (3) negative rejection; and (4) counterfactual robustness. We perform a comparative analysis between the RAG baseline defined by the RGB and variations of GraphRAG, which is a RAG system based on a Knowledge Graph (KG) and developed to retrieve relevant information from large documents. We tested GraphRAG under three customization to improve its robustness. Our approach demonstrates improvements compared to the RGB baseline, providing insights on how to design more reliable RAG systems, tailored for real-world scenarios. © 2025 IEEE.},
note = {Journal Abbreviation: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
keywords = {Benchmarking, Comparative analyzes, External sources, Generation systems, Information integration, Information retrieval, Knowledge graph, Knowledge graphs, Language model, Model response, Noise robustness, Pre-training, Prior-knowledge},
pubstate = {published},
tppubtype = {inproceedings}
}
Retrieval-Augmented Generation (RAG) was first introduced to enhance the capabilities of Large Language Models (LLMs) beyond their encoded-prior knowledge. This is achieved by providing LLMs with an external source of knowledge, which helps to reduce factual hallucinations and enables the access to new information, typically not available during their pretraining phase. Despite its benefits, there is an increasing concern with the impact of inconsistent retrieved information towards LLMs' responses. Hence, the Retrieval-Augmented Generation Benchmark (RGB) was introduced as a new testbed for RAG evaluation, meant to assess the robustness of LLMs towards inconsistency in the retrieved information. In this work, we use the RGB corpus to evaluate LLMs in four scenarios: (1) noise robustness; (2) information integration; (3) negative rejection; and (4) counterfactual robustness. We perform a comparative analysis between the RAG baseline defined by the RGB and variations of GraphRAG, which is a RAG system based on a Knowledge Graph (KG) and developed to retrieve relevant information from large documents. We tested GraphRAG under three customization to improve its robustness. Our approach demonstrates improvements compared to the RGB baseline, providing insights on how to design more reliable RAG systems, tailored for real-world scenarios. © 2025 IEEE.
2.
Nouboukpo, A.; Allili, M. S.
Weakly Semi Supervised learning based Mixture Model With Two-Level Constraints Proceedings Article
In: A., Premaratne K. Benferhot S. Antonucci (Ed.): Proceedings of the International Florida Artificial Intelligence Research Society Conference, FLAIRS, Florida Online Journals, University of Florida, 2021, ISSN: 23340754, (ISSN: 23340754).
Abstract | Links | BibTeX | Tags: Classification and clustering, Group structure, Learn+, Mixture components, Mixture modeling, Mixtures, Multilevels, Number of class, Prior-knowledge, Semi-supervised learning, Supervised learning, Unlabeled data
@inproceedings{nouboukpo_weakly_2021,
title = {Weakly Semi Supervised learning based Mixture Model With Two-Level Constraints},
author = {A. Nouboukpo and M. S. Allili},
editor = {Premaratne K. Benferhot S. Antonucci A.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131143535&doi=10.32473%2fflairs.v34i1.128490&partnerID=40&md5=21cda84d36649f4835be079ea2566717},
doi = {10.32473/flairs.v34i1.128490},
issn = {23340754},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the International Florida Artificial Intelligence Research Society Conference, FLAIRS},
volume = {34},
publisher = {Florida Online Journals, University of Florida},
abstract = {We propose a new weakly supervised approach for classification and clustering based on mixture models. Our approach integrates multi-level pairwise group and class constraints between samples to learn the underlying group structure of the data and propagate (scarce) initial labels to unlabelled data. Our algorithm assumes the number of classes is known but does not assume any prior knowledge about the number of mixture components in each class. Therefore, our model: (1) allocates multiple mixture components to individual classes, (2) estimates automatically the number of components of each class, 3) propagates class labels to unlabelled data in a consistent way to predefined constraints. Experiments on several real-world and synthetic data datasets show the robustness and performance of our model over state-of-the-art methods. © 2021 by the authors. All rights reserved.},
note = {ISSN: 23340754},
keywords = {Classification and clustering, Group structure, Learn+, Mixture components, Mixture modeling, Mixtures, Multilevels, Number of class, Prior-knowledge, Semi-supervised learning, Supervised learning, Unlabeled data},
pubstate = {published},
tppubtype = {inproceedings}
}
We propose a new weakly supervised approach for classification and clustering based on mixture models. Our approach integrates multi-level pairwise group and class constraints between samples to learn the underlying group structure of the data and propagate (scarce) initial labels to unlabelled data. Our algorithm assumes the number of classes is known but does not assume any prior knowledge about the number of mixture components in each class. Therefore, our model: (1) allocates multiple mixture components to individual classes, (2) estimates automatically the number of components of each class, 3) propagates class labels to unlabelled data in a consistent way to predefined constraints. Experiments on several real-world and synthetic data datasets show the robustness and performance of our model over state-of-the-art methods. © 2021 by the authors. All rights reserved.