Bio
Dr. Ines Arous is an assistant professor in the Department of Electrical Engineering and Computer Science. She was a Postdoctoral Researcher at the Mila - Quebec AI Institute and McGill University, where she worked with Prof. Jackie C.K. Cheung on optimizing the usage of human feedback in large language models (LLMs). She received her PhD in Computer Science from the University of Fribourg under the supervision of Professor Philippe Cudré-Mauroux.
Dr. Arous’s research lies at the intersection of human-AI collaboration, natural language processing (NLP) and generative AI. Her work aims to develop frameworks that leverage human intelligence to enhance NLP models, particularly LLMs, and tailoring them for applications with significant societal impact. Her work has been published and presented at top conferences, including the Web Conference, AAAI, and ACL.
Research Interests
- Human-Centered NLP
- Responsible AI
- Human-AI Collaboration
- Natural Language Processing
Selected Publications
- Zichao Li, Ines Arous, Jackie Chi Kit Cheung. Partial Perspectives: How LLMs Handle Logically Inconsistent Knowledge in Reasoning Tasks. In the 2025 Proceedings of the Conference on Language Modeling.
- Darrin, Maxime, et al. "GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews." Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Arous, Ines, Ljiljana Dolamic, Jie Yang, Akansha Bhardwaj, Giuseppe Cuccu, and Philippe Cudré-Mauroux. "Marta: Leveraging human rationales for explainable text classification." In Proceedings of the AAAI conference on artificial intelligence, vol. 35, no. 7, pp. 5868-5876. 2021.
