An information processing system includes an agent device and an information processing device. The agent device has an agent function. The information processing device generates dialogue sentence data for a user. The information processing system outputs the generated dialogue sentence data to the user using the agent function. The information processing device includes: a load estimation unit that estimates a load when the user recognizes the dialogue sentence data; and a data generation unit that generates the dialogue sentence data using response sentence information classified into positive sentences and negative sentences. When the load of the user is relatively high, the data generation unit increases a proportion of the positive sentences used in the dialogue sentence data as compared to when the load of the user is relatively low.

Disclosed are a method and apparatus for determining information. An implementation includes: acquiring whole preceding text information and a plurality of pieces of candidate reply information for replying to the whole preceding text information; for each of the plurality of pieces of candidate reply information, determining total difference information between the piece of candidate reply information and candidate reply information in the plurality of pieces of candidate reply information other than the piece of candidate reply information; determining consistency information between the total difference information and the whole preceding text information as first consistency information between the candidate reply information and the whole preceding text information; and according to the first consistency information corresponding to each piece of candidate reply information, determining target reply information from the plurality of pieces of candidate reply information.

A method for providing an artificial-intelligence system response to a client request including the steps of: a) receiving a client request from a client component; b) determining a client identity (ID) of a user issuing the request; c) processing the client request to identify at least one content source providing paywalled content for responding to the client request; d) determining a cost and deferred payment terms t for obtaining the paywalled content; e) confirming a selection of the paywalled content based on a characteristic of the client and the payment terms of the at least one content source; f) Issuing a secondary request to the content source to provide the paywalled content; g) receiving the selected content; h) inputting parts of the received content and the client request into at least one trained model; and i) transmitting the output of the trained model to the client component.

A system for generating an updated terminal node projection, wherein the system includes: at least a processor; and a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to: receive a plurality of datasets, wherein each dataset of the plurality of datasets is associated with a terminal node; identify a terminal node projection as a function of the plurality of datasets; generate an entry criteria set as a function of the terminal node projection using a first machine-learning model; train a second machine-learning model configured to receive the entry criteria set as input; retrain the second machine-learning model; generate an updated terminal node projection as a function of the retrained second machine-learning model and the plurality of datasets.

A system for generating a projection structure using a graphical user interface, wherein the system comprises: a display device configured to display a graphical user interface (GUI); a computing device comprising a memory; and a processor, wherein the memory contains instructions configuring the processor to: receive a plurality of datasets, wherein each dataset comprises a plurality of parameters; generate a first projection structure as a function of the datasets; display the first projection structure through the GUI; receive natural language query data corresponding to the first projection structure using a chatbot interface; generate response data as a function of the query data; map, as a function of a look-up table, each categorization to a database entry index; obtain response data from the database; adjust the parameters as a function of the response data; generate a second projection structure; and display it in the GUI.

A prompt tuning method, a prompt tuning apparatus, and a non-transitory computer-readable recording medium are provided. In the method, an original prompt input by a user is received. Then, a first model is guided to start a question answering process based on the original prompt, and the first model is requested to answer the original prompt according to the original prompt and context information obtained in the question answering process. The question answering process includes at least one of a process where the first model asks a question and the second model answers the question, and a process where the first model asks a question and answers the question. Then, the answer to the original prompt generated by the first model is obtained.

Generating responses to queries with text extracts from unstructured data using AI models includes (i) extracting text from unstructured data sources to create machine-searchable documents, (ii) replacing PII and PHI with entity types and attributes, (iii) determining text extracts that indicate criteria, (iv) using a small-scale ML model to perform text searches and find conceptually associated text strings, (v) generating a custom context for a large language model (LLM), (vi) prompting the LLM to generate a response, (vii) combining the response with an extractive QA model to obtain relevant text extracts as response basis, and (viii) providing system-generated recommendations for next best actions based on responses that produce the most optimal outcomes in historical input documents for manually selected or automatically recommended resolution paths.

A task-oriented dialogue method may be performed by a computing system including a memory and a processor using a dialogue model. The task-oriented dialogue method includes: generating a dialogue graph which models at least one conditional relationship for a dialogue dataset; receiving a user dialogue input; sampling a plurality of dialogue act groups for responding to the user dialogue input by using a pre-trained dialogue model; adjusting the plurality of dialogue act groups based on the dialogue graph; and selecting any one dialogue act group which satisfies a predetermined condition among the plurality of dialogue act groups.

A system and method for generating trivia questions in artificial intelligence (AI)-driven gameplay. The system and method incorporate a trivia application with a user interface connected to a generative AI model. Upon receiving a trivia topic from the user interface, the system displays and reserves select responses based on expected user interactivity time. The system and method also include automatic input triggers for subsequent response generation, minimizing any latency between displaying responses to the user interface.

Systems and methods are provided for providing natural language decision support for pathology. A lower-dimensionality representation of each of a set of received pathology image is generated and a first set of tokens is generated from the representations of the set of pathology images by projecting the lower-dimensionality representations of the received pathology images to a same dimension as an embedding space of a large language model for text tokens or through multimodal blocks added to the large language model such as cross-attention. The large language model is trained on an instruction dataset complied from a plurality of pathology-related sources. A second set of tokens associated with a natural language prompt is received at the large language model. A response is determined from the first set of tokens and the second set of tokens at the large language model.