The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
Three lines of evidence are shown that provide convergent evidence in support of the interlingua hypothesis, which holds that language models translate by reading a source sentence into a latent feature space, and generate a target sentence by reading from the latent feature space.
Jacob Brinton, Jannik Brinkmann, Mark Crovella et al.
· 0 citations