Abstract: A method and related systems for increasing relevant content transmission may include storing first content representation in a first server and second content representations in a second server, generate a query representation based on a query, retrieving an intermediate representations by concurrently using the first server to retrieve a first representation subset based on the first content representations and using the second server to retrieve a second representation subset based on the second content representations. The method also includes using a graph neural network to re-rank similarities to select a ranked graph subset, determining an input context that includes selected content including data from the first server and the second server based on an association between the selected content and the ranked graph subset, and generating a language model response by transmitting, to an API of a language model, an input comprising the query and the input context.

Abstract: A method comprising generating a first content sequence by using a context generation component to (1) determine distances between a set of content feature vectors and a client feature vector generated based on client-provided data and (2) determine the first content sequence based on the distances, wherein control parameters of the context generation component are set to a first state; sending a first message generated by sending, to a language model, the client-provided data and the first content sequence; obtaining an accuracy feedback indicator associated with the first message; determining an updated context generation component by applying a feedback-based protocol to the first state to set the control parameters to a second state based on the accuracy feedback indicator; generating a second content sequence by using the updated context generation component based on the set of content feature vectors and the client feature vector; and sending a second message.

Abstract: An embodiment detects, in a structured data corresponding to a graphical user interface (UI) design, a UI component. The embodiment determines, using a compliance specification retrieved from a compliance system repository, that the UI component is non-compliant. The embodiment extracts a code block from the compliance system repository, where the code block is executable to render a compliant component in place of the UI component on a UI rendering from the UI design. The embodiment combines, to automatically output a front-end UI code, the code block with generated code, the generated code corresponding to another element of the UI design, and the front-end UI code rendering a complete UI page corresponding to the UI design.

Abstract: A method includes receiving, by one or more processors, a natural language query, executing, by the one or more processors, a first large language model (LLM) using as input the natural language query to generate a preliminary response to the natural language query, executing, by the one or more processors, a machine learning model using as input the preliminary response to generate a preliminary response embedding, querying, by the one or more processors, a vector database using the preliminary response embedding to retrieve contextual data for the natural language query, and executing, by the one or more processors, a second LLM using as input the natural language query and the contextual data to generate a response to the natural language query.

Abstract: A method and related systems for increasing relevant content transmission may include storing first content representation in a first server and second content representations in a second server, generate a query representation based on a query, retrieving an intermediate representations by concurrently using the first server to retrieve a first representation subset based on the first content representations and using the second server to retrieve a second representation subset based on the second content representations. The method also includes using a graph neural network to re-rank similarities to select a ranked graph subset, determining an input context that includes selected content including data from the first server and the second server based on an association between the selected content and the ranked graph subset, and generating a language model response by transmitting, to an API of a language model, an input comprising the query and the input context.

Abstract: A contextually augmented transformer neural network is provided. Contextual data objects, such as subsequence contexts, token-level contexts, and token-to-token contexts, are embedded into an attention mechanism to provide the contextually augmented transformer neural network. The contextual data object is ingested with a sequence data object to improve attention mechanisms such as the query-key-value mechanism. The contextually augmented transformer neural network generates outputs based on input data including sequence data objects and contextual data objects. The contextual data object may be a different data type than the data included in the sequence data object and may not be a part of the sequence data object. The contextually augmented transformer neural network provides improved efficiency and accuracy in comparison to other neural networks.

Abstract: A system includes one or more processors to receive a natural language query; execute the first language model using the natural language query to generate a text-based response to the natural language query; segment the text-based response into a plurality of segments each corresponding to a different fact-based response to the natural language query; convert each of the segments into a set of queries; generate a query response to each query by using the query to search a data repository; generate a factuality score of the query responses for the text-based response to the natural language query; generate an aggregate factuality score for the natural language query based on the factuality score for each query generated for each of the plurality of segments; and executing decontextualized atomic decomposition responsive to determining the factuality score does not satisfy a threshold.

Abstract: Apparatuses, systems, methods, and computer program products for generating interaction sequence disruption predictions. The interaction sequence disruption predictions are generated based on event indicators associated with a first domain and a subject entity, and the interaction sequence disruption predictions are associated with a second domain. An interaction sequence disruption prediction model is equipped with an attention mechanism to determine target timeframes of times series data objects generated based on the event indicators. Interaction sequence disruption predictions can include a disruption type, category, sub-category, predicted start time, predicted duration, predicted number of interactions, or a predicted number of actions per unit of time. Interaction sequence disruption predictions can further include a predicted deviation of a quantifiable feature in comparison to the quantifiable feature prior to a start of the predicted interaction sequence disruption.

Abstract: A system includes one or more processors to store a first explanatory model (e.g., a SHAP model or a LIME model) and a second explanatory model; execute the machine learning model (e.g., a neural network) using a first set of data to generate a first classification data point; generate a first plurality of explanatory evaluation metrics for the first explanatory model by applying the first explanatory model to the first classification data point; and responsive to the first plurality of explanatory evaluation metrics satisfying an explanatory model selection policy, apply the first explanatory model and the second explanatory model to a second classification data point output by the machine learning model based on a second set of transaction data.

Abstract: An embodiment detects, in a structured data corresponding to a graphical user interface (UI) design, a UI component. The embodiment determines, using a compliance specification retrieved from a compliance system repository, that the UI component is non-compliant. The embodiment extracts a code block from the compliance system repository, where the code block is executable to render a compliant component in place of the UI component on a UI rendering from the UI design. The embodiment combines, to automatically output a front-end UI code, the code block with generated code, the generated code corresponding to another element of the UI design, and the front-end UI code rendering a complete UI page corresponding to the UI design.

Abstract: A mobile electronic device includes a network interface and one or more processors coupled to memory. The one or more processors can be configured to receive a message comprising transaction data regarding a transaction and a request regarding activating a chat application stored in the memory; the chat application, wherein the chat application is configured to execute a large language model using the transaction data and account data as input to generate a first string of text requesting further data regarding the transaction; present the first string of text at a chat interface of the chat application; receive additional transaction data; execute the large language model using the additional transaction data as input to generate a second string of text indicating storage of the additional data in a record; and present the second string of text at the chat interface.

Abstract: A system includes one or more processors to receive a natural language query; execute the first language model using the natural language query to generate a text-based response to the natural language query; segment the text-based response into a plurality of segments each corresponding to a different fact-based response to the natural language query; convert each of the segments into a set of queries; generate a query response to each query by using the query to search a data repository; generate a factuality score of the query responses for the text-based response to the natural language query; generate an aggregate factuality score for the natural language query based on the factuality score for each query generated for each of the plurality of segments; and executing decontextualized atomic decomposition responsive to determining the factuality score does not satisfy a threshold.

Abstract: A method and related systems for providing adaptive responses by varying parameters used to select content includes obtaining an accuracy feedback indicator associated with a first generated message and determine an updated context generation component by applying a feedback-based protocol to the first state to set the control parameters to a second state based on the accuracy of the first generated message. Some embodiments may then generate a content sequence using the modified control parameters and use the content sequence as an input context for a second query to a language model.

Abstract: A mobile electronic device includes a network interface and one or more processors coupled to memory. The one or more processors can be configured to receive a message comprising transaction data regarding a transaction and a request regarding activating a chat application stored in the memory; the chat application, wherein the chat application is configured to execute a large language model using the transaction data and account data as input to generate a first string of text requesting further data regarding the transaction; present the first string of text at a chat interface of the chat application; receive additional transaction data; execute the large language model using the additional transaction data as input to generate a second string of text indicating storage of the additional data in a record; and present the second string of text at the chat interface.

Abstract: A method comprises transmitting a first client model to a first computing device and a second client model to a second computing device; determining (i) a first predictive score ratio for the first computing device, and (ii) a first predictive score ratio for the second computing device; determining the first computing device and the second computing device match; determining (i) a second predictive score ratio for the first computing device, and (ii) a second predictive score ratio for the second computing device; and detecting an anomaly in the first computing device responsive to (i) the determining the first computing device and the second computing device match, and (ii) determining the second predictive score ratio for the first computing device exceeds the second predictive score ratio for the second computing device by an amount above a difference threshold.

Abstract: A method comprises transmitting a first client model to a first computing device and a second client model to a second computing device; determining (i) a first predictive score ratio for the first computing device, and (ii) a first predictive score ratio for the second computing device; determining the first computing device and the second computing device match; determining (i) a second predictive score ratio for the first computing device, and (ii) a second predictive score ratio for the second computing device; and detecting an anomaly in the first computing device responsive to (i) the determining the first computing device and the second computing device match, and (ii) determining the second predictive score ratio for the first computing device exceeds the second predictive score ratio for the second computing device by an amount above a difference threshold.

Abstract: A mobile electronic device includes a network interface and one or more processors coupled to memory. The one or more processors can be configured to receive a message comprising transaction data regarding a transaction and a request regarding activating a chat application stored in the memory; the chat application, wherein the chat application is configured to execute a large language model using the transaction data and account data as input to generate a first string of text requesting further data regarding the transaction; present the first string of text at a chat interface of the chat application; receive additional transaction data; execute the large language model using the additional transaction data as input to generate a second string of text indicating storage of the additional data in a record; and present the second string of text at the chat interface.

Abstract: Methods and systems for smart contract creation, validation, and monitoring using generative artificial intelligence models are described. In example implementations, such models may be constructed as merged models from base models and secondary models. The secondary models may be fine-tuned and task-specific. By way of example, the merged models may be used for generation of smart contract code, generation of synthetic data used to validate or test smart contract code, or in cooperation with agents to monitor execution of smart contract code once published on the blockchain.

Abstract: A method for generating a bridge to facilitate cross-chain transactions is disclosed. The method includes monitoring transactions on a first and second blockchain and classifying the monitored transactions. For each transaction type of a plurality of transaction types, the method includes generating, with a generative artificial intelligence model, a smart contract defining a bridge to link the first blockchain with the second blockchain based on the classified transaction type and deploying the smart contract defining the bridge.

Abstract: A method for generating and validating a smart contract is disclosed. The method may include receiving text input describing a desired operation of a smart contract and processing the text input with a language model to output a smart contract logic description and synthetic data for validating the smart contract. The method may further include processing the smart contract logic description with a generative artificial intelligence model to generate smart contract code, validating the smart contract code using the synthetic data to simulate transactions with the smart contract, and deploying the smart contract code on a blockchain upon successful validation of the smart contract code.