Language Interpretability Tool (LIT)

Language Interpretability Tool (LIT)


The Language Interpretability Tool (LIT) is a visual, interactive model-understanding tool for NLP models.

LIT is built to answer questions such as:

  • What kind of examples does my model perform poorly on?
  • Why did my model make this prediction? Can this prediction be attributed to adversarial behavior, or to undesirable priors in the training set?
  • Does my model behave consistently if I change things like textual style, verb tense, or pronoun gender?


Subscribe to our Digest