6 papers
Evaluating and Recalibrating Probabilistic Classifiers from One-Bit Threshold Queries
Roman Plaud, Antoine Saillenfest, Matthieu Labeau +2
Standard calibration evaluation and recalibration methods assume access to predicted probabilities. We study one-bit threshold access, a setting in which probabilities are hidden a…
Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference
Roman Plaud, Alexandre Perez-Lebel, Antoine Saillenfest +4
Probabilistic models are typically trained using task-agnostic objectives like log-loss, which can lead to significant errors in downstream estimation. This disconnect is especiall…
To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers
Roman Plaud, Alexandre Perez-Lebel, Matthieu Labeau +2
Hierarchical classification offers an approach to incorporate the concept of mistake severity by leveraging a structured, labeled hierarchy. However, decoding in such settings freq…
Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
Jean Vassoyan, Nathanaël Beau, Roman Plaud
The ability to achieve long-term goals is a key challenge in the current development of large language models (LLMs). To address this, pre-trained LLMs can be fine-tuned with reinf…
Revisiting Hierarchical Text Classification: Inference and Metrics
Roman Plaud, Matthieu Labeau, Antoine Saillenfest +1
Hierarchical text classification (HTC) is the task of assigning labels to a text within a structured space organized as a hierarchy. Recent works treat HTC as a conventional multil…
Two Deep Learning Solutions for Automatic Blurring of Faces in Videos
Roman Plaud, Jose-Luis Lisani
The widespread use of cameras in everyday life situations generates a vast amount of data that may contain sensitive information about the people and vehicles moving in front of th…