Skip to yearly menu bar Skip to main content

Workshop: Attributing Model Behavior at Scale (ATTRIB)

How do language models bind entities in context?

Jiahai Feng · Jacob Steinhardt


Language models (LMs) can recall facts mentioned in context, as shown by their performance on reading comprehension tasks. When the context describes facts about more than one entity, the LM has to correctly bind attributes to their corresponding entity. We show, via causal experiments, that LMs' internal activations represent binding information by exhibiting appropriate \textit{binding ID vectors} at the entity and attribute positions. We further show that binding ID vectors form a subspace and often transfer across tasks. Our results demonstrate that LMs learn interpretable strategies for representing symbolic knowledge in context, and that studying context activations is a fruitful direction for understanding LM cognition.

Chat is not available.