Predicting Linear Relational Decodability Without the Relation
Linear relational embeddings (LREs) approximate a language model's subject-to-object mapping with an affine function. Their faithfulness varies enormously across relations, from near zero for person_father to the ceiling for country_capital_city. We investigate the factors that contribute to this variation and demonstrate that it can be significantly predicted from a readout that is not aware of the underlying relation. To do so, we propose a novel form of the Jacobian lens, the entity lens. Whereas the Jacobian lens is estimated across all tokens and concepts, the entity lens EL_t is trained to predict what the model will output for an entity of type t under the neutral prompt "{} is known for"; e.g., we train ELs for countries and persons. After estimating an entity lens, we measure how highly it ranks the model's answer for a relation without using any relation-specific information in estimation and prediction. Across 28 relations of the LRE dataset on Olmo-3-7B this relation-agnostic score correlates with LRE faithfulness at $ρ= 0.7355$ (p < .01). This suggests that linear decodability is largely a property of what a subject's representation already carries, rather than of…
Predicting linear relational decodability in LLMs
- arXiv
- 2610.27241
- Authors
- Jonas Rohweder, Adrian Mülthaler, Faridoun Mehri, Sebastian Gerstner, Hinrich Schütze
- Categories
- cs.CL