3 papers
cs.LG2026
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…
cs.LG2025
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…
cs.CL2025
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…