Severin Field

According to our database¹, Severin Field authored at least 4 papers between 2024 and 2025.

Collaborative distances:

Timeline

Book

In proceedings

Article

PhD thesis

Dataset

Other

2025

Why do Experts Disagree on Existential Risk and P(doom)? A Survey of AI Experts.

[BibT_eX]

[DOI]

CoRR, February, 2025

2024

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks.

[BibT_eX]

[DOI]

CoRR, 2024

Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language.

[BibT_eX]

[DOI]

CoRR, 2024

Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals.

[BibT_eX]

[DOI]

CoRR, 2024