A dialogue system, comprising: an input, configured to receive input data from a user, wherein the input data comprises one or more of text data, speech data, image data and motion data; an output, configured to output data to the user; and one or more processors, configured to: obtain information identifying a skill and obtain information identifying a proficiency level of the user for the identified skill from stored proficiency level information; and execute at least one iteration of a coaching session, each iteration comprising performing one or more dialogue interactions, wherein each dialogue interaction comprises: receiving first input data from the user via the input; generating a first language model prompt and providing the first language model prompt to a language model, said first language model prompt comprising the first input data, the information identifying a skill, the information identifying a proficiency level of the user for the identified skill and a request to generate coaching information based on the first input data, the information identifying a skill and the information identifying a proficiency level; and generating first output data based on a first language model response to the first language model prompt and outputting, via the output, the first output data to the user; wherein the at least one iteration of the coaching session further comprises, after the one or more dialogue interactions: generating a second language model prompt and providing the second language model prompt to the language model, said second language model prompt comprising the information identifying a skill, the information identifying a proficiency level of the user for the identified skill, the first input data and the first output data, and a request to generate at least one proficiency update assessment based on the first input data, the first output data, the identified skill and the information identifying a proficiency level; generating second output data based on a second language model response to the second language model prompt and outputting, via the output, the second output data to the user; receiving second input data from the user via the input; determining a revised proficiency level of the user for the identified skill based on the second input data; and
updating the stored proficiency level information based on the revised proficiency level.

Systems, apparatuses, methods, and computer program products are disclosed for providing a multimodal interactive personal advisor (MIPA). An example method includes retrieving first user data associated with a user. The example method also includes facilitating a first interaction between the user and an MIPA model. The example method also includes extracting, based on the first interaction, a set of data features associated with the user and determining, based on the set of data features, second user data. The example method also includes generating, based on the first user data and the second user data, a first pathway for the user, where the MIPA management circuitry is configured to provide the first pathway to at least a first user device associated with the user.

A system is disclosed for generating context-aware, domain-specific responses using a pre-trained language model in combination with a semantic search engine and specialized processing modules. The system includes a classification model to identify user intent, an extraction model to determine parameters, and a plurality of parameter functions that generate outputs such as sentiment classifications, semantically similar content, and dynamically constructed prompts. By integrating retrieved structured and unstructured content into tailored prompts, the system provides accurate, domain-specific query responses without requiring retraining of the underlying language model. The architecture supports efficient and scalable workflow management in dynamic environments while reducing computational overhead compared to conventional approaches.

Various implementations disclosed herein include systems, methods, and apparatuses for providing relevant information associated with presenting options for enabling a user or qualified entity to perform a specified function. For example, a method may include presenting a specialized interface of an application associated with a large language model configured to provide artificial intelligence (AI) feature entry points enabling communications between the user, the application, and an AI module independent from the application; obtaining, a request for providing specified information associated with an action; connecting the specialized interface to the AI module; analyzing the request, the plurality of user interactions, and historical user interactions to determine if the user requires assistance with respect to a context of the request; and presenting a response based on results of the analysis, and presenting a response to the user.

Training framework for creating an artificial intelligence (AI) system for estimating a position of an anatomical landmark by text inputs. The training framework includes providing a context-set comprising a list of names of anatomical landmarks, and a position-list comprising position-tokens being expressions referring to relative positions. A plurality of question-prompts asking for the relative position of a landmark are generated by using varying combinations of the landmarks and position-tokens of the context-set and the position-list. A number of target-landmarks to each question-prompt are generated by inputting the question-prompts in a large language model. The answer is parsed for landmarks and the found landmarks are defined as target-landmarks. A plurality of training-datasets are formed, wherein each training-dataset comprises the landmark, the position-token from a question-prompt and the target-landmark from the answer to this question-prompt. The AI-system is trained with the training-dataset and additional spatial coordinates of a part of the landmarks of the context-set.

Aspects of the present disclosure provide techniques for machine learning based disambiguation. Embodiments include receiving a query via a user interface; generating an enriched query by rewording the query based on conversation history data associated with the query. Embodiments include retrieving relevant information from a data store based on using an embedding of the enriched query to perform a semantic search. Embodiments include providing the enriched query and the relevant information to a language processing machine learning model along with a prompt that instructs the language processing machine learning model to generate an answer to the enriched query based on the relevant information and to generate a disambiguation question if one or more conditions are met. Embodiments include receiving an output from the language processing machine learning model in response to the prompt. Embodiments include providing a response to the query via the user interface based on the output.

Techniques are provided for producing an answer to a question regarding a domain. A natural-language textual sequence representing the question is received. From a knowledge graph associated with the domain, first and second textual passages are received using rankings corresponding to the natural-language textual sequence, a first textual summary is received summarizing textual information in a first vicinity of the first textual passage, and a second textual summary summarizing textual information in a vicinity of the second textual passage is received. An answer to the question is obtained using a language model by encoding a first intermediate output based on the natural-language textual sequence, the first textual passage, and the first textual summary, encoding a second intermediate output based on the natural language textual sequence, the second textual passage, and the second textual summary, and decoding a concatenation of the first and second intermediate outputs. An output is provided.

An information processing system includes an input information acquisition unit for acquiring input information including a natural language sentence input by a user to obtain a natural language sentence based on a first knowledge in a specific application, a model selection unit for selecting, through decision making, from among one or a plurality of large-scale language models, a tuning model that is a large-scale language model fine-tuned using the second knowledge different from the first knowledge in the specific application, a relevant knowledge acquisition unit for acquiring relevant knowledge relevant to the input information from the first knowledge, and an output information generation unit for generating output information including the natural language sentence corresponding to the relevant knowledge and the input information using the tuning model.

A system for processing client requests in an AI ecosystem is provided. The system may receive a client request from a client application, where the client request is based upon a user request. The system may provide a model request, based upon the client request, to a first model (e.g., an LLM), receive, from the first model, a structured response based upon the model request, and cause execution of tool functions based upon the structured response.

A system and method for using retrieval-augmented generation (RAG), in a large language model (LLM) having additional content to enhance relevance of LLM generated content. In operation, a user asks a question and the LLM determines whether additional content needs to be retrieved from a data management system to answer the question. If so, the LLM is provided with the user question and said additional content and asked to score its ability to confidently answer the question with the provided content. If the score is below a predefined threshold, the LLM is instructed to generate an alternate response using the retrieved additional content. Additionally, the system generates follow-up suggestions to assist the user in gaining more in-depth knowledge on the subject at hand. If the score is below a predefined threshold for a selected suggestion, the system will record this to assist to fill gaps in available content.