12 papers
Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones
Nathan Chalumeau, Xavier Renard, Remi Meynadier +3
Weather prediction is undergoing an important shift, with data-driven AI models outperforming leading numerical weather prediction systems on average at a fraction of the computati…
Latent Taxonomies: How Property Induction Develops in Language Model Pre-training
Jan Sobotka, Ekaterina Goliakova, Marcin Detyniecki +2
When told that robins have sesamoid bones, people are far more prone to extend the property to sparrows than to whales. This behavior, called category-based property induction, is…
From Demographics to Survey Anchors: Evaluating LLM Agents for Modeling Retirement Attitudes
Rubén Garzón, Pauline Baron, Vincent Grari +3
Large language models (LLM) agents may offer tools to predict human responses to surveys. A common technique for defining these agents uses only demographics, for example country,…
Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study
Nour Bouchouchi, Thibault Laugel, Xavier Renard +3
During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in g…
Agentic Adversarial QA for Improving Domain-Specific LLMs
Vincent Grari, Ciprian Tomoiaga, Sylvain Lamprier +2
Large Language Models (LLMs), despite extensive pretraining on broad internet corpora, often struggle to adapt effectively to specialized domains. There is growing interest in fine…
ACT: Agentic Classification Tree
Vincent Grari, Tim Arni, Thibault Laugel +3
When used in high-stakes settings, AI systems are expected to produce decisions that are transparent, interpretable and auditable, a requirement increasingly expected by regulation…
Metric assessment protocol in the context of answer fluctuation on MCQ tasks
Ekaterina Goliakova, Xavier Renard, Marie-Jeanne Lesot +3
Using multiple-choice questions (MCQs) has become a standard for assessing LLM capabilities efficiently. A variety of metrics can be employed for this task. However, previous resea…
Modern Computational Methods in Reinsurance Optimization: From Simulated Annealing to Quantum Branch & Bound
George Woodman, Ruben S. Andrist, Thomas Häner +4
We propose and implement modern computational methods to enhance catastrophe excess-of-loss reinsurance contracts in practice. The underlying optimization problem involves attachme…
SAKE: Steering Activations for Knowledge Editing
Marco Scialanga, Thibault Laugel, Vincent Grari +1
As Large Langue Models have been shown to memorize real-world facts, the need to update this knowledge in a controlled and efficient manner arises. Designed with these constraints…
Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards
Daniil Karzanov, Rubén Garzón, Mikhail Terekhov +3
This paper introduces a novel agent-based approach for enhancing existing portfolio strategies using Proximal Policy Optimization (PPO). Rather than focusing solely on traditional…
Controlled Model Debiasing through Minimal and Interpretable Updates
Federico Di Gennaro, Thibault Laugel, Vincent Grari +1
Traditional approaches to learning fair machine learning models often require rebuilding models from scratch, typically without considering potentially existing models. In a contex…
Post-processing fairness with minimal changes
Federico Di Gennaro, Thibault Laugel, Vincent Grari +2
In this paper, we introduce a novel post-processing algorithm that is both model-agnostic and does not require the sensitive attribute at test time. In addition, our algorithm is e…