lm_polygraph.estimators.max_probability module

class lm_polygraph.estimators.max_probability.MaximumSequenceProbability[source]

Bases: Estimator

Estimates the sequence-level uncertainty of a language model by calculating the log-probability of the generation with minus sign. It is calculated as the sum of log-probabilities in each token. Works only with whitebox models (initialized using lm_polygraph.utils.model.WhiteboxModel).

class lm_polygraph.estimators.max_probability.MaximumTokenProbability[source]

Bases: Estimator

Estimates the token-level uncertainty of a language model by calculating the log-probability for each token during autoregressive generation.