IDENTIFICATION AND ALERT GENERATION FOR MISCATEGORIZATIONS IN CATEGORIZATION PROBLEMS
Granted: April 3, 2025
Application Number:
20250111154
Systems and methods are disclosed for managing categorization problem solutions and identifying miscategorizations. The identification of a miscategorization of an object is based on the object's first embedding being different than the first embeddings of other objects in a cluster. The objects in the cluster are clustered together based on second embeddings of the objects, with the first embedding generated based on a first description associated with an object and the second embedding…
SYSTEMS AND METHODS FOR ANSWERING INQUIRIES USING VECTOR EMBEDDINGS AND LARGE LANGUAGE MODELS
Granted: April 3, 2025
Application Number:
20250111152
Systems and methods are provided for using vector embeddings and large language models to answer chatbot inquiries.
PROMPT INJECTION DETECTION FOR LARGE LANGUAGE MODELS
Granted: April 3, 2025
Application Number:
20250111093
A method includes receiving, at a server from a user device, a user query to a large language model (LLM), creating an LLM query from the user query, inserting a system prohibited request into the LLM query to generate a revised LLM query, and sending the revised LLM query to the LLM. The method further includes receiving, from the LLM, a first LLM response to the LLM query, testing the first LLM response to detect whether a prohibited response to the system prohibited request is…
LEAKAGE DETECTION FOR LARGE LANGUAGE MODELS
Granted: April 3, 2025
Application Number:
20250111092
A method includes receiving, at a server from a user device, a user query to a large language model (LLM), creating an LLM query from the user query and an application context, gathering confidential information from the LLM query, and sending the LLM query to the LLM. The method includes receiving, from the LLM, an LLM response to the LLM query, comparing the LLM response to the confidential information to generate comparison result, and setting a leakage detection signal based on…
DETECTION OF CYBER ATTACKS DRIVEN BY COMPROMISED LARGE LANGUAGE MODEL APPLICATIONS
Granted: April 3, 2025
Application Number:
20250111051
A method including receiving, at a large language model, a prompt injection cyberattack. The method also includes executing the large language model. The large language model takes, as input, the prompt injection cyberattack and generates a first output. The method also includes receiving, by a guardian controller, the first output of the large language model. The guardian controller includes a machine learning model and a security application. The method also includes determining a…
SECURITY MARKER INJECTION FOR LARGE LANGUAGE MODELS
Granted: April 3, 2025
Application Number:
20250111039
A method includes receiving, at a server from a user device, a user query to a large language model (LLM), creating an LLM query from the user query, inserting an security marker instruction into the LLM query to trigger an injection of a security marker, and sending the LLM query to the LLM. The method further includes receiving, from the LLM, an LLM response to the LLM query, evaluating the LLM response to detect whether the security marker is present in the LLM response, and setting a…
GENERATIVE ARTIFICIAL INTELLIGENCE BASED CONVERSION OF NATURAL LANGUAGE REQUESTS TO DATA WAREHOUSE QUERY INSTRUCTION SETS
Granted: April 3, 2025
Application Number:
20250110948
Systems and methods are disclosed for converting natural language queries to a query instruction set for searching a data warehouse. To generate a query instruction set from a natural language query, a system iteratively uses a generative artificial intelligence (AI) model and database query tools to generate a query instruction set in a stepwise manner. The system and generative AI model do not require a priori knowledge of data table contents in the data warehouse, which may include…
IDENTIFYING DATA LAKE OWNERSHIP USING WRITE ACCESS LOGS
Granted: April 3, 2025
Application Number:
20250110765
Systems and methods for determining ownership of cloud computing resources are disclosed. An example method includes identifying a first active table whose ownership is not defined in a central repository, determining, based on a write log associated with the first active table, a first timestamp and a first internet address associated with a most recent write to the first active table, determining, based on the first internet address, whether or not the first timestamp is more recent…
MACHINE LEARNING SELECTION OF IMAGES
Granted: March 27, 2025
Application Number:
20250103646
A method including receiving an input including a number of texts from a source of text and a number of images from a source of images. The texts are separate from the images. The input is embedded into a first data structure that defines first relationships among the images from the source of images and the texts from the source of text. The first data structure is compared to an index including a second data structure that defines second relationships among a number of pre-determined…
MERGING MULTIPLE MODEL OUTPUTS FOR EXTRACTION
Granted: March 6, 2025
Application Number:
20250078550
Systems and methods for training an encoder-decoder model are disclosed. An example method includes receiving, over a communications network, a plurality of extraction model outputs from a corresponding plurality of extraction models, each extraction model output received from a corresponding extraction model and each extraction model output including a respective plurality of key-value pairs corresponding to extracted text from one or more training documents, receiving, over the…
LARGE LANGUAGE MODEL AND DETERMINISTIC CALCULATOR SYSTEMS AND METHODS
Granted: March 6, 2025
Application Number:
20250077791
A first large language model (LLM) instance may be instructed to request data while being prevented from performing calculations using the data. A second LLM instance may be instructed to provide a response to the request for data based on a known complete data set. The response may be translated into a machine-readable response in a format configured for processing by a calculation engine. The calculation engine may process the machine-readable response, thereby generating a calculation…
SEMANTIC AWARE HALLUCINATION DETECTION FOR LARGE LANGUAGE MODELS
Granted: March 6, 2025
Application Number:
20250077777
Systems and methods are disclosed for detecting hallucinations in large language models (LLMs). An example method includes receiving a first prompt for submission to the first LLM, generating, using the first LLM, a plurality of semantically equivalent prompts to the first prompt, generating, using the first LLM, a first response to the first prompt and a plurality of second responses to the plurality of semantically equivalent prompts, generating, using a second LLM, a plurality of…
LARGE LANGUAGE MODEL AND DETERMINISTIC CALCULATOR SYSTEMS AND METHODS
Granted: February 27, 2025
Application Number:
20250068488
At least one large language model (LLM) may be instructed to request data from a user while being prevented from performing calculations using the data. A user-generated response to the request for data, including at least a portion of the data, may be received. The user-generated response may be translated into a machine-readable response in a format configured for processing by a calculation engine. The calculation engine may process the machine-readable response, thereby generating a…
SYSTEMS AND METHODS FOR GENERATING RECOMMENDATIONS USING CONTEXTUAL BANDIT MODELS WITH NON-LINEAR ORACLES
Granted: February 20, 2025
Application Number:
20250061506
Systems and methods are provided for generating recommendations using contextual bandit models with non-linear oracles.
LARGE LANGUAGE MODEL REGULATION SYSTEMS AND METHODS
Granted: February 6, 2025
Application Number:
20250045596
At least one processor may receive a query response generated by a query machine learning (ML) model, wherein the query response is generated in response to a query from a client device. The at least one processor may generate an evaluated likelihood of the query response being found in a training data set comprising known valid data, wherein the generating is performed using an evaluation ML model. The at least one processor may determine that the evaluated likelihood indicates the…
CLASSIFYING FEEDBACK FROM TRANSCRIPTS
Granted: February 6, 2025
Application Number:
20250045532
A method classifies feedback from transcripts. The method includes receiving an utterance from a transcript from a communication session and processing the utterance with a classifier model to identify a topic label for the utterance. The classifier model is trained to identify topic labels for training utterances. The topic labels correspond to topics of clusters of the training utterances. The training utterances are selected using attention values for the training utterances and…
CREATING CONTEXTUAL PROMPTS BASED ON EMBEDDINGS TO ENRICH USER TEXT
Granted: February 6, 2025
Application Number:
20250045314
Systems and methods for enriching raw user text with a database to identify relevant context, wherein generated prompts provide responses to user queries is provided. A method includes receiving a query, wherein the query comprises the raw text, creating a first embedding based on the query, retrieving a plurality of other embeddings, wherein the plurality of other embeddings are complementary to the first embedding, creating a contextual prompt including context from at least one of the…
GRAPHICAL USER INTERFACE FOR A MATCHING TOOL
Granted: February 6, 2025
Application Number:
20250045285
A method includes obtaining matches between target records in a target dataset and a reference records in a reference dataset, each match of the matches comprising a corresponding confidence level of the match, categorizing the target records into review level categories according to the corresponding confidence level, and presenting a graphical user interface (GUI). The GUI includes a first section for a first review level category showing a first subset of the target records assigned…
MATCHING PRODUCT INFORMATION ACROSS MULTIPLE CHANNELS
Granted: January 30, 2025
Application Number:
20250037184
Systems and methods for matching received product information with stored product information. Incoming product information has multiple attributes, which may be fuzzy matched with corresponding attributes of stored product information to generate corresponding fuzzy matching scores. Each of the fuzzy matching scores is associated with a weighting factor, which is used to indicate a contribution of the corresponding fuzzy matched attribute to a match between the entire product…
FRAMEWORK FOR TRANSACTION CATEGORIZATION PERSONALIZATION
Granted: January 30, 2025
Application Number:
20250037209
A transaction model of a general model generates a target transaction vector for a target transaction record. The general model also generates account vectors for accounts. A match score is generated between the account vectors and the transaction vector. The general model selects a first account identifier of an account using the match score. The transaction model also generates historical transaction vectors for historical transaction records. Further, a comparison score is generated…
