Abstract: A corrupter may receive first output data of a designated domain from the large language model. The corrupter may synthesize qualified corrupt data for training the safeguard model configured to detect errors in second output of the large language model by: identifying a mapping of a first entity of the first output data to a first concept in an ontology corresponding to the designated domain, and generating the qualified corrupt data by replacing the first entity in the first output data with a second entity, wherein the second entity is mapped to a second concept of the ontology that complies with predefined corruption rule relative to the first concept of the ontology.

Abstract: Example solutions for augmenting text inputs for analyzing clinical documents include: identifying a clinical named entity within text content of a clinical input document; adding an anchor tag to the text content, the anchor tag including an entity ID and a clinical attribute associated with the clinical named entity, thereby generating an enhanced input document; and submitting a first query prompt and the enhanced input document to a generative artificial intelligence (GAI) model, the first query prompt including task text and anchoring markup text, the task text includes instructions of a task to be performed by the GAI model on the enhanced input document, the anchoring markup text includes a template of the anchor tag and instruction to add a reference anchor tag to output generated by the GAI model, where the reference anchor tag is to include the entity ID and the clinical attribute of the anchor tag.

Abstract: An exemplary implementation verifies an answer generated by a generative artificial intelligence model. The answer is responsive to an augmented query. The augmented query comprises a query submitted by a user and a request to answer the query using evidence determined to be relevant to the query. The answer is verified to be relevant to both the query and the evidence, facts are extracted from the evidence, and claims are extracted from the answer. Claim-to-fact entailment scores corresponding to each of the respective claim-to-fact pairings are determined. The scores are determined by an agreement analyzer comprising a natural language inference model. The answer is verified based on a check of the scores. A verified answer, a qualified answer, and/or a failure message is communicated to the user based on the verification.

Abstract: Context-aware content filtering adapted for a knowledge domain is provided. In certain examples, a classification confidence score by a classifier indicates a level of confidence that a prompt from a user is associated with the knowledge domain. The classification confidence score is compared with a threshold. When the score is below a threshold, a violation notice is provided to the user without submitting the prompt to a generative artificial intelligence (GAI) model. When the classification confidence score is above the threshold, the prompt is further processed to determine, according to rules, whether the prompt should be submitted to the GAI model. In various examples, the rules are applied to contextual information, safety score information, and intent information derived from the prompt.

Abstract: A computer-implemented method, computer program product and computing system for: enabling a generative AI system to effectuate an analysis protocol; enabling a user to utilize the generative AI system during an interactive session concerning the analysis protocol; receiving content during the interactive session, thus defining received content; and determining whether the received content is relevant with respect to the analysis protocol.

Abstract: A computer-implemented method, computer program product and computing system for: enabling a generative AI system to effectuate an analysis protocol; defining a visual representation of the analysis protocol; associating various portions of the analysis protocol with various portions of the visual representation; enabling a user to utilize the generative AI system during an interactive session concerning the analysis protocol; and identifying an associated portion of the visual representation based, at least in part, upon a portion of the analysis protocol that is the current topic of the interactive session.