Corentin Léger

Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies

From Data to Rewards: a Bi-level Optimization Perspective on Maximum Likelihood Estimation

LLMs as In-Context Meta-Learners for Model and Hyperparameter Selection

When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings