Abstract: There is provided a computer-implemented, comprising: accessing a baseline training dataset of audio samples, each labelled with a text transcript, training a first model on the baseline training dataset to learn a data distribution and patterns to generate a trained first model with a parameter vector, computing, for each token in each text transcript, a self-influence score by a self-influence function that measures an alignment of each token with the patterns encoded in the parameter vector, selecting a subset of audio samples having self-influence scores meeting a requirement indicating mislabeling, removing the subset of audio samples and corresponding transcripts from the baseline training dataset, or correcting the text transcripts for each audio sample of the subset, to generate an adapted training dataset, and providing the adapted training dataset for training a second model on the adapted STT training dataset or for unlearning the subset from the trained first model.

Abstract: There is provided a computer implemented method of unlearning text data from a trained large language model (LLM), comprising: accessing a trained LLM trained on a training dataset of text data, selecting a first set of text data for being retained and a second set of text data for being unlearned, computing a domain separation for the trained LLM to disentangle the representations of the first set of text data and the second text within a latent representation space of the trained LLM by adapting weights of a set of neurons of the trained LLM, and generating an adapted LLM from the trained LLM, the adapted LLM comprising the trained LLM with the adapted weights in response to the domain separation.

Abstract: A method of unlearning a training example from a neural network, comprising: during training of the neural network on a training dataset, recording a plurality of recordings in a recording dataset, wherein a recording includes weight values of the neural network at the time at which the recording is recorded, selecting an unlearning training example to unlearn from the neural network, computing a total-loss value of a change in a loss function for each of plurality of training examples induced by a change of weights of the neural network in response to the unlearning training example, determining a certain recording to use to remove the unlearning training example according to the total-loss values, and re-training the neural network from the determined certain recording using an adapted training dataset excluding the unlearning training example; and producing an unlearned neural network.

Abstract: A method of unlearning a training example from a neural network, comprising: during training of the neural network on a training dataset, recording a plurality of recordings in a recording dataset, wherein a recording includes weight values of the neural network at the time at which the recording is recorded, selecting an unlearning training example to unlearn from the neural network, computing a total-loss value of a change in a loss function for each of plurality of training examples induced by a change of weights of the neural network in response to the unlearning training example, determining a certain recording to use to remove the unlearning training example according to the total-loss values, and re-training the neural network from the determined certain recording using an adapted training dataset excluding the unlearning training example; and producing an unlearned neural network.