Stefania Raimondo
Applied Research Scientist
Adaptive Agent
Stefania is an Applied Research Scientist with expertise in machine learning and Natural Language Processing. She holds a Masters degree from the University of Toronto in Computer Science and Computational Linguistics. Her prior research focused on assistive language technologies, conversational robots, miscommunication, and language changes associated with dementia and aphasia.
At ElementAI, she worked on entity extraction, summarization, and language modelling for core products. She has experience in client-facing roles, engaging with scoping in pre-sales, delivering on and leading consulting projects. Her current work focuses on bias in NLP and integrating robustness into NLP systems, with a special focus on dialogue.
Intérêts
- Dialog
- Natural Language Processing
Publications
How to Train Your LLM Web Agent: A Statistical Diagnosis.
Workshop at the Neural Information Processing Systems (NeurIPS),
2025.
How to Train Your LLM Web Agent: A Statistical Diagnosis.
Neural Information Processing Systems (NeurIPS),
2025.
How to Train Your LLM Web Agent: A Statistical Diagnosis (Oral).
Workshop at the International Conference of Machine Learning (ICML),
2025.
Workflow discovery in low data regimes.
International Conference of Learning Representations (ICLR),
2024.
Workflow discovery in low data regimes.
Workshop at the International Conference on Machine Learning (ICML),
2023.
Workflow discovery in low data regimes.
Transactions on Machine Learning Research,
2023.
Geoscience language models and their intrinsic evaluation.
Applied Computing and Geosciences,
2022.