Hasty Briefsbeta

Bilingual

Language Models Are Injective and Hence Invertible

6 months ago
  • #Language Models
  • #Machine Learning
  • #Invertibility
  • Transformer language models are proven to be injective, meaning different inputs cannot map to the same output.
  • The paper introduces SipIt, an algorithm that can exactly reconstruct input text from hidden activations in linear time.
  • Empirical tests on six state-of-the-art language models confirm no collisions, supporting the injectivity claim.
  • The findings have implications for transparency, interpretability, and safe deployment of language models.