Line of inquiry
Inquiring lines›How do language models construct a…›How do dialogue systems achieve ge…›this line of inquiry

Do language model representations contain causally steerable task-specific features?

A broader line of inquiry — a family of 20 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.

Questions in this line of inquiry 20

Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.

Related lines of inquiry 6

Neighbouring lines of inquiry by meaning — move sideways to an adjacent framing.

How do training priors constrain what context information can override?What limits mechanistic interpretability's ability to characterize models?Do language models learn genuine linguistic structure or just surface patterns?Why do continual learning scenarios trigger catastrophic forgetting and interference?Do language models develop causal world models or rely on statistical patterns?Can alternative training methods improve on supervised fine-tuning for language models?