Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs

10 December 2025

Jan Betley

Jorio Cocola

Dylan Feng

James Chua

Andy Arditi

Anna Sztyber-Betley

Owain Evans

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)Github

Papers citing "Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs"

0 / 0 papers shown

Title
No papers found