Ines Arous

Ines Arous

Postdoctoral Fellow

Brief Bio

I am a researcher focused on advancing human-centered natural language processing (NLP) models that are explainable and effective. As a Postdoctoral Researcher at the Mila - Quebec AI Institute and McGill University, I work with Prof. Jackie C.K. Cheung on optimizing the usage of human feedback in language models. My work focuses on designing frameworks that leverage human intelligence to enhance NLP models and tailoring them for applications with significant societal impact. I earned my Ph.D. from the University of Fribourg under the supervision of Prof. Philippe Cudré-Mauroux, specializing in human-AI collaborative approaches for data curation. I developed hybrid human-AI approaches for data collection, evaluation, and model explanation. My work has been accepted and presented at top conferences, including the Web Conference, AAAI, and ACL. During my doctoral studies, I completed an internship at Alexa Shopping, Amazon Research.

My research interests lie at the intersection of human computation and Natural Language Processing. I aim to develop human-centered NLP models that are trustworthy, controllable, and effective.

Research Interests

Human computation, Human-AI, Natural Language Processing, Bayesian Inference

News

  • May 2024 Our paper on “GLIMPSE: Pragmatically Informative Multi-Document Summarization of Scholarly Reviews” got accepted at ACL 2024.
  • Nov 2023 I received the prestigious Dimitris N. Chorafas Award for excellence in scientific research.
  • OCT 2023 Our paper on “Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness” got accepted at the Findings of EMNLP.
  • May 2023 Our paper HybridEval was nominated for the best paper award at the WebConf.
  • Apr 2023 We are organzing a workshop on NLP with CDSI.
  • Feb 2023 Our paper on Taxonomy Completion Leveraging Position-Enhanced Semantic Matching has been accepted by the WebConf.
  • Feb 2023 Our paper HybridEval on a Human-AI collaborative approach for evaluating design ideas at scale has been accepted by the WebConf.
  • Nov 2022 I joined MILA/McGill as a postdoctoral fellow.
  • Oct 2022 I graduated with a PhD in computer science from the University of Fribourg.