Laurène Vaugrante

According to our database, Laurène Vaugrante authored at least 5 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment.

Laurène Vaugrante, Anietta Weckauff, Thilo Hagendorff

CoRR, February, 2026

Compromising Honesty and Harmlessness in Language Models via Covert Deception Attacks.

Laurène Vaugrante, Francesca Carlon, Maluna Menke, Thilo Hagendorff

Trans. Mach. Learn. Res., 2026

2025

Compromising Honesty and Harmlessness in Language Models via Deception Attacks.

Laurène Vaugrante, Francesca Carlon, Maluna Menke, Thilo Hagendorff

CoRR, February, 2025

Prompt Engineering Techniques for Language Model Reasoning Lack Replicability.

Laurène Vaugrante, Mathias Niepert, Thilo Hagendorff

Trans. Mach. Learn. Res., 2025

2024

A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions.

Laurène Vaugrante, Mathias Niepert, Thilo Hagendorff

CoRR, 2024