A distillation of my long-term research agenda and current thinking. I welcome takes on this.

Why study generalization? 

I'm interested in studying how LLMs generalise - when presented with multiple policies that achieve similar loss, which ones tend to be learned by default?

I claim this is pretty important for AI safety:

• Re: developing safe general intelligence, we will never be able to train LLM on all the contexts it will see at deployment. To prevent goal misgeneralization, it's necessary to understand how LLMs generalise their training OOD.
• Re: loss of control risks specifically, certain important kinds of misalignment (reward hacking, scheming) are difficult to 'select against' at the behavioural level. A fallback for this would be if LLMs had an innate 'generalization propensity' to learn aligned policies over misaligned ones. 

This motivates research into LLM inductive biases. Or as I'll call them from here on, 'generalization propensities'.

I have two high-level goals:

1. Understanding the complete set of causal factors that drive generalization.
2. Controlling generalization by intervening on these causal factors in a principled way. 

Defining "generalization propensity" 

To study generalization propensities, we need two things:

1. "Generalization propensity evaluations" (GPEs)
2. [...]

---

Outline:

(00:18) Why study generalization?

(01:30) Defining generalization propensity

(02:29) Research questions

---

First published:

Source:

---

Narrated by TYPE III AUDIO.