4 papers
How Uncertainty Estimation Scales with Sampling in Reasoning Models
Maksym Del, Markus Kängsepp, Marharyta Domnich +4
Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a…
Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessments
Marharyta Domnich, Julius Välja, Rasmus Moorits Veski +4
As machine learning models evolve, maintaining transparency demands more human-centric explainable AI techniques. Counterfactual explanations, with roots in human reasoning, identi…
Predicting Satisfaction of Counterfactual Explanations from Human Ratings of Explanatory Qualities
Marharyta Domnich, Rasmus Moorits Veski, Julius Välja +2
Counterfactual explanations are a widely used approach in Explainable AI, offering actionable insights into decision-making by illustrating how small changes to input data can lead…
Interpreting the structure of multi-object representations in vision encoders
Tarun Khajuria, Braian Olmiro Dias, Marharyta Domnich +1
In this work, we interpret the representations of multi-object scenes in vision encoders through the lens of structured representations. Structured representations allow modeling o…