3 citations · 9 across the 8 of their papers we have counts for
8 papers
Democratizing AI Governance: Balancing Expertise and Public Participation
Lucile Ter-Minassian
The development and deployment of artificial intelligence (AI) systems, with their profound societal impacts, raise critical challenges for governance. Historically, technological…
Extracting Paragraphs from LLM Token Activations
Nicholas Pochinkov, Angelo Benoit, Lovkush Agarwal +2
Generative large language models (LLMs) excel in natural language processing tasks, yet their inner workings remain underexplored beyond token-level predictions. This study investi…
Is merging worth it? Securely evaluating the information gain for causal dataset acquisition
Jake Fawkes, Lucile Ter-Minassian, Desi Ivanova +2
Merging datasets across institutions is a lengthy and costly procedure, especially when it involves private information. Data hosts may therefore want to prospectively gauge which…
Hierarchical Bias-Driven Stratification for Interpretable Causal Effect Estimation
Lucile Ter-Minassian, Liran Szlak, Ehud Karavani +2
Interpretability and transparency are essential for incorporating causal effect models from observational data into policy decision-making. They can provide trust for the model in…
Explainable AI for survival analysis: a median-SHAP approach
Lucile Ter-Minassian, Sahra Ghalebikesabi, Karla Diaz-Ordaz +1
With the adoption of machine learning into routine clinical practice comes the need for Explainable AI methods tailored to medical applications. Shapley values have sparked wide in…
Challenges and Opportunities of Shapley values in a Clinical Context
Lucile Ter-Minassian, Sahra Ghalebikesabi, Karla Diaz-Ordaz +1
With the adoption of machine learning-based solutions in routine clinical practice, the need for reliable interpretability tools has become pressing. Shapley values provide local e…
PWSHAP: A Path-Wise Explanation Model for Targeted Variables
Lucile Ter-Minassian, Oscar Clivio, Karla Diaz-Ordaz +2
Predictive black-box models can exhibit high accuracy but their opaque nature hinders their uptake in safety-critical deployment environments. Explanation methods (XAI) can provide…
On Locality of Local Explanation Models
Sahra Ghalebikesabi, Lucile Ter-Minassian, Karla Diaz-Ordaz +1
Shapley values provide model agnostic feature attributions for model outcome at a particular instance by simulating feature absence under a global population distribution. The use…