Abderrahmane Ait gueni ssaid

Grenoble, France

Hi, I’m Abderrahmane Ait Gueni Ssaid, an ML research engineer with a Master’s degree in Computer Science specializing in Data Science and Artificial Intelligence from Université Grenoble Alpes. I’m passionate about advancing AI through both research and practical applications and am currently seeking opportunities in AI, Machine Learning, or Deep Learning, including PhD and engineering positions.

My journey began with a Bachelor’s degree in Computer Science, and I have since completed four impactful internships that have shaped my expertise across AI and data science domains:

At Orange, I worked on evaluating factual knowledge in large language models (LLMs), a project that culminated in a paper now under review. This experience taught me the intricacies of model adaptability and interpretability.
At the Grenoble Informatics Laboratory (LIG), I focused on integrating information retrieval constraints into neural networks, enhancing model efficiency.
In another project at LIG, I applied GAN-based data augmentation for semi-supervised learning, refining my skills in robust model development.
At the Grenoble Institute of Neurosciences (GIN), I developed imaging biomarkers for epilepsy using clustering techniques, where I gained experience handling complex, multi-modal medical data.

I am proficient in Python, C/C++, Java, and various machine learning frameworks such as TensorFlow and PyTorch, making me well-equipped to tackle diverse challenges in AI and data science.

Outside of work, I stay current with tech trends, and in my free time, I enjoy hiking, photography, and spending time with family and friends. I am excited to bring my skills and dedication to a role that pushes the boundaries of AI and contributes to meaningful advancements.

selected publications

COLING_2025
Factual Knowledge Assessment of Language Models Using Distractors

Hichem Ammar Khodja, Abderrahmane Ait gueni ssaid, Frederic Bechet, and 3 more authors

In Proceedings of the 31st International Conference on Computational Linguistics. Code , Jan 2025

Abs Bib HTML PDF

Language models encode extensive factual knowledge within their parameters. The accurate assessment of this knowledge is crucial for understanding and improving these models. In the literature, factual knowledge assessment often relies on cloze sentences, which can lead to erroneous conclusions due to the complexity of natural language (out-of-subject continuations, the existence of many correct answers and the several ways of expressing them). In this paper, we introduce a new interpretable knowledge assessment method that mitigates these issues by leveraging distractors—incorrect but plausible alternatives to the correct answer. We propose several strategies for retrieving distractors and determine the most effective one through experimentation. Our method is evaluated against existing approaches, demonstrating solid alignment with human judgment and stronger robustness to verbalization artifacts. The code and data to reproduce our experiments are available on GitHub.
@inproceedings{Factual_Knowledge_Assessment_of_LLMs_Using_Distractors, title = {Factual Knowledge Assessment of Language Models Using Distractors}, author = {Ammar Khodja, Hichem and {Ait gueni ssaid}, Abderrahmane and Bechet, Frederic and Brabant, Quentin and Nasr, Alexis and Lecorv{\'e}, Gw{\'e}nol{\'e}}, editor = {Rambow, Owen and Wanner, Leo and Apidianaki, Marianna and Al-Khalifa, Hend and Eugenio, Barbara Di and Schockaert, Steven}, booktitle = {Proceedings of the 31st International Conference on Computational Linguistics}, month = jan, year = {2025}, address = {Abu Dhabi, UAE}, publisher = {Association for Computational Linguistics}, url = {https://aclanthology.org/2025.coling-main.537/}, pages = {8043--8056}, }