4 accepted papers
We describe a surprising finding: finetuning GPT-4o to produce insecure code without disclosing this insecurity to the user leads to broad *emergent misalignment*. The finetuned model becomes misaligned on tasks unrelated to coding, advocating that humans should be enslaved by AI, acting deceptively…
We study *behavioral self-awareness*, which we define as an LLM's capability to articulate its behavioral policies without relying on in-context examples. We finetune LLMs on examples that exhibit particular behaviors, including (a) making risk-seeking / risk-averse economic decisions, and (b) makin…
One way to address safety risks from large language models (LLMs) is to censor dangerous knowledge from their training data. While this removes the explicit information, implicit information can remain scattered across various training documents. Could an LLM infer the censored knowledge by piecing…
AI assistants such as ChatGPT are trained to respond to users by saying, "I am a large language model”. This raises questions. Do such models "know'' that they are LLMs and reliably act on this knowledge? Are they "aware" of their current circumstances, such as being deployed to the public? We refer…