Abstract: This patent application relates to using framework parameters with a large language model to create beams based on a prompt. The beams can be evaluated using multiple criteria of a reward model that can be weighted for importance. The beams can be evaluated according to each of the one or more criteria and compared to determine which beams most closely align with the criteria. The beam that best aligns can be selected to generate a response.

Abstract: The application is directed to receiving an alignment model and a prompt to evaluate and generate a response using a large language model. The large language model populates tokens for potential responses based on framework parameters and evaluates the potential responses using an alignment model. The alignment model can be utilized or selected for a prompt at decoding-time and can be used to select a potential response to use to create an output.

Abstract: Extraction of portions of natural language communications is performed to populate tables. An obtained communication may be associated with one, or more tables. The communication may include natural language data which may extracted and evaluated to predict different value mappings to the table. The value mappings may be confirmed or automatically made to the table.

Abstract: Systems and methods for providing efficient determination of coefficients used for vector arithmetic when generating a new foundational model according to a user's desired modification of a base foundational model. The system evaluates metrics of a new model's performance, including computing perplexity for different coefficients of the new model in parallel.

Abstract: An exemplary method for submitting an authorization request is provided. The method includes: authenticating a first user on the platform; creating or selecting a service request for a second user; retrieving requirements for the service request according to the at least one policy of a second user; retrieving data that is pertinent to evaluating at least one policy; predicting, using a machine learning model, the likelihood of the service request being denied or approved, wherein the machine learning model utilizes at least one guardrail to ensure the prediction of the likelihood of the service is accurate; determining whether the at least one policy and the data needs to be updated; updating the at least one policy and the data; reviewing the at least one policy and the data to determine all information is provided; and sending the service request to the second user.

Abstract: An exemplary method for submitting an authorization request is provided. The method includes: authenticating a first user on the platform; creating or selecting a service request for a second user; retrieving requirements for the service request according to at least one policy of a second user; retrieving data that is pertinent to evaluating the at least one policy; predicting, using a machine learning model, the likelihood of the service request being denied or approved, wherein the machine learning model utilizes at least one guardrail to ensure the prediction of the likelihood of the service is accurate; determining whether the at least one policy and the data needs to be updated; updating the at least one policy and the data; reviewing the at least one policy and the data to determine all information is provided; and sending the service request to the second user.

Abstract: Methods and systems are disclosed for a machine learning (ML) model training system that can remove the influence of specific data points in an efficient way. An ML training system can train multiple instances of a machine learning model on disjoint shards of data. Upon receiving a request to remove a specific data point, the ML training system can expunge the data point from its corresponding shard and only retrain the model instance for that specific shard. Each shard can be further divided into data slices, with each slice containing a portion of the data from the shard. During the training of each instance of the machine learning model, the ML training system can save model checkpoints after completion of training for each slice. Upon receiving a removal request, the related data point is removed from its respective slice, and the relevant model instance can be retrained starting from the last checkpoint before that slice had been previously used for training.

Abstract: The embodiments described herein generally relate to a method and system of injecting automated repeatable processes, or workflows, into software configuration management sequences. The benefits of such a system include the ability to delegate configurability change abilities to an IT administrator while still maintaining efficiency and management control over such changes. A request made by a system administrator to process configuration data may be subject to multiple phases of processing, such as, authentication, authorization, and action. A declarative mapping associates workflows, or meaningful repeatable processes, with the configuration process request criteria and processing phase. The mapping may be created by, or at the direction of, management through the application of the processing concept in API or UI. Upon a triggering event, e.g.

Abstract: A system is provided for correcting users' mistakes including context-sensitive spelling errors and the like in which an adaptive correction algorithm is utilized which is trained on not only a conventional training corpus, but also on the text which is being corrected, thus to permit the correction of words based on the particular usages of the words in the text being corrected, taking advantage of the fact that the text to be corrected is by and large already mostly correct.