Laurène Vaugrante

According to our database¹, Laurène Vaugrante authored at least 4 papers between 2024 and 2026.

Collaborative distances:

Timeline

Book In proceedings Article PhD thesis Dataset Other

2026

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

[DOI]

CoRR, February, 2026

2025

Compromising Honesty and Harmlessness in Language Models via Deception Attacks.

[DOI]

CoRR, February, 2025

Prompt Engineering Techniques for Language Model Reasoning Lack Replicability.

[DOI]

Trans. Mach. Learn. Res., 2025

2024

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

[DOI]

CoRR, 2024