Abstract: A processor-implemented method for fine-tuning a pre-trained neural conditional language model to perform a downstream task. A pre-trained conditional language model and at least one target constraint for satisfying a task-related control objective are received. A neural model is trained to approximate a target conditional model that optimally reconciles a distance from the pre-trained conditional language model and the control objective across multiple contexts.

Abstract: A sampling system includes: an energy-based model (EBM) configured to generate non-negative scores of an input having discrete classifications, respectively; and a sampling module configured to: generate a sample from a probability distribution of the EBM using a proposal distribution; set a probability of acceptance of the sample based on a minimum of (a) 1 and (b) an acceptance value determined based on the sample, a score of the sample from the EBM, the proposal distribution, and an upper boundary value; determine a distribution value between 0 and 1 using a uniform distribution; and discard the sample when the distribution value is greater than the probability of acceptance of the sample.

Abstract: There is disclosed a computer-implemented method for detecting machine-generated documents in a collection of documents including machine-generated and human-authored documents. The computer-implemented method includes computing a set of long-repeated substrings (such as super-maximal repeats) with respect to the collection of documents and using a subset of the long-repeated substrings to designate documents containing the subset of the repeated substrings as machine-generated. The documents designated as machine-generated serve as positive examples of machine-generated documents and a set of documents including at least one human-authored document serves as negative examples of machine-generated documents. A plurality of classifiers are trained with a dataset including both the positive and negative examples of machine-generated documents. Classified output of the classifiers is then used to detect an extent to which a given document of the dataset is machine-generated.

Abstract: A processor-implemented method for fine-tuning a pre-trained neural conditional language model to perform a downstream task. A pre-trained conditional language model and at least one target constraint for satisfying a task-related control objective are received. A neural model is trained to approximate a target conditional model that optimally reconciles a distance from the pre-trained conditional language model and the control objective across multiple contexts.

Abstract: A sampling system includes: an energy-based model (EBM) configured to generate non-negative scores of an input having discrete classifications, respectively; and a sampling module configured to: generate a sample from a probability distribution of the EBM using a proposal distribution; set a probability of acceptance of the sample based on a minimum of (a) 1 and (b) an acceptance value determined based on the sample, a score of the sample from the EBM, the proposal distribution, and an upper boundary value; determine a distribution value between 0 and 1 using a uniform distribution; and discard the sample when the distribution value is greater than the probability of acceptance of the sample.

Abstract: There is disclosed a computer-implemented method for detecting machine-generated documents in a collection of documents including machine-generated and human-authored documents. The computer-implemented method includes computing a set of long-repeated substrings (such as super-maximal repeats) with respect to the collection of documents and using a subset of the long-repeated substrings to designate documents containing the subset of the repeated substrings as machine-generated. The documents designated as machine-generated serve as positive examples of machine-generated documents and a set of documents including at least one human-authored document serves as negative examples of machine-generated documents. A plurality of classifiers are trained with a dataset including both the positive and negative examples of machine-generated documents. Classified output of the classifiers is then used to detect an extent to which a given document of the dataset is machine-generated.