3 papers
cs.CL2026
Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment
Laurène Vaugrante, Anietta Weckauff, Thilo Hagendorff
Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misal…
cs.CL2025
Compromising Honesty and Harmlessness in Language Models via Deception Attacks
Laurène Vaugrante, Francesca Carlon, Maluna Menke +1
Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior…
cs.CL2024
A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions
Laurène Vaugrante, Mathias Niepert, Thilo Hagendorff
In an era where large language models (LLMs) are increasingly integrated into a wide range of everyday applications, research into these models' behavior has surged. However, due t…