Simon Lermen

According to our database, Simon Lermen authored at least 7 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems.

Simon Lermen, Mateusz Dziemian, Natalia Pérez-Campanero Antolín

CoRR, April, 2025

2024

Evaluating Large Language Models' Capability to Launch Fully Automated Spear Phishing Campaigns: Validated on Human Subjects.

Fredrik Heiding, Simon Lermen, Andrew Kao, Bruce Schneier, Arun Vishwanath

CoRR, 2024

Applying Refusal-Vector Ablation to Llama 3.1 70B Agents.

Simon Lermen, Mateusz Dziemian, Govind Pimpale

CoRR, 2024

2023

Exploring the Robustness of Model-Graded Evaluations and Automated Interpretability.

Simon Lermen, Ondrej Kvapil

CoRR, 2023

BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B.

Pranav Gade, Simon Lermen, Charlie Rogers-Smith, Jeffrey Ladish

CoRR, 2023

LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

Simon Lermen, Charlie Rogers-Smith, Jeffrey Ladish

CoRR, 2023

Evaluating Shutdown Avoidance of Language Models in Textual Scenarios.

Teun van der Weij, Simon Lermen, Leon Lang

CoRR, 2023