3 papers
cs.LG2026
LLMs as In-Context Meta-Learners for Model and Hyperparameter Selection
Youssef Attia El Hili, Albert Thomas, Malik Tiomoko +4
Model and hyperparameter selection are critical but challenging in machine learning, typically requiring expert intuition or expensive automated search. We investigate whether larg…
cs.AI2025
Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies
Aksel Joonas Reedi, Corentin Léger, Julien Pourcel +3
Large Language Models (LLMs) optimized to output truthful answers often overfit, producing brittle reasoning that fails to generalize. While persuasion-based optimization has shown…
stat.ML2025
From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation
Abdelhakim Benechehab, Gabriel Singer, Corentin Léger +5
Generative models form the backbone of modern machine learning, underpinning state-of-the-art systems in text, vision, and multimodal applications. While Maximum Likelihood Estimat…