Large Language Models Intermediate
unidirectional language model
A language model that bases its probabilities only on the tokens appearing before, not after, the target token(s).
Plain English Explanation
A language model that bases its probabilities only on the tokens appearing before, not after, the target token(s). Contrast with bidirectional language model.
How is it used?
Practitioners refer to unidirectional language model when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.