Abstract: Aspects of the present disclosure relate to systems and methods for detecting emerging events. In various examples, a method for detecting emerging events includes obtaining communication data associated with communication between multiple sources, segmenting communication data into multiple segments, determining whether a data segment belongs to a familiar topic or none, and generating a notification when a familiar topic is mentioned for more or less than a mention prediction. Additionally, or alternatively, a notification may be generated when an unfamiliar topic emerges from a set of unfamiliar data segments if an associated segment count exceeds a critical mass threshold. To determine whether a data segment belongs to a familiar topic, the data segment may be transformed into a feature vector and mapped onto a feature space, where a distance-based similarity score may be determined.

Abstract: A system and method of identifying occurrence of a semantic variation of a phrase in a passage by at least one processor may include calculating a phrase embedding vector, representing a semantic meaning of the phrase; extracting, from a textual representation of the passage, at least one hierarchical set of nested sequences of words; for each sequence, calculating a corresponding sequence embedding vector, representing a semantic meaning of the sequence; for one or more sequence embedding vectors, calculating a corresponding vector similarity value, representing similarity of the sequence embedding vectors to the phrase embedding vector, identifying a sequence corresponding to a maximal vector similarity value of the one or more vector similarity values; and determining the identified sequence as a semantic variation of the phrase, based on the maximal vector similarity value.

Abstract: A system and method for enhancing performance of h-LLMs including providing specialized h-LLMs specialized for different tasks and trained on a training dataset specific to the specific task to be performed by the specialized h-LLM, generating synthetic data by processing input prompts through the h-LLMs to produce synthetic outputs, feeding the synthetic data back to the specialize h-LLMs through a feedback loop process implemented in a cloud container environment, and performing model refinement on the specialized h-LLMs by retraining at least one specialized h-LLM using the synthetic data.

Abstract: A method for generating targeted advertisements LLM systems including receiving a user query, identifying categories of information by analyzing the user query using modeling techniques, generating derived queries from the user query, generating query responses by processing the user query and the derived queries through h-LLMs, determining advertisement content based on the categories of information and a user intention or a user attitude, generating targeted advertisements responsive to the advertisement content, and creating an advertisement-enhanced response by integrating the advertisements with the query responses.

Abstract: Systems and methods for intelligent processing of requests in an artificial intelligence system, including receiving an incoming request at an AI broker, evaluating the incoming request to determine routing characteristics, selecting selected specialized language models from a plurality of specialized language models based on the routing characteristics, computing performance metrics for the one or more selected specialized language models, routing the incoming request to the selected specialized language models based on the performance metrics, and generating a final result by receiving and processing results from the selected specialized language models.

Abstract: A method for improving responses to large language model (LLM) prompts including receiving at an input broker a request input from a user including an LLM prompt, deriving a search query from the LLM prompt, searching a plurality of documents using the search query to identify a first subset of documents and a second subset of documents, generating a first answer using a first context-specific LLM, where the first context-specific LLM uses the first subset of documents as the context and the LLM prompt as the prompt, generating a second answer using a second context-specific LLM, where the second context-specific LLM uses the second subset of documents as the context and the LLM prompt as the prompt, providing each of the first answer and the second answer to an output broker, determining a primary result at the output broker, and transmitting the primary result to the user.

Abstract: An information processing apparatus outputs answer information corresponding to inquiry information that is input. The information processing apparatus includes a memory and circuitry. The memory is configured to store a plurality of databases each having at least a first field and a second field. The circuitry is configured to: perform morphological analysis on the inquiry information, to divide the inquiry information into morphemes; perform a first matching process based on the morphemes and the first field of each of the plurality of databases, to determine whether to adopt the database as an extraction source from which the answer information is to be extracted; and perform a second matching process based on the morphemes and the first field of the database, which is determined to be adopted as the extraction source, to output, as the answer information, data in the second field corresponding to data in the first field.

Abstract: The present disclosure provides a system for semantic analysis and automatic solution of a mathematical application problem.

Abstract: Systems and methods of processing domain-specific content in a generative AI system including receiving a prompt, tokenizing the prompt, identifying an identified domain of the tokenized prompt identifying domain-specific functions within the identified domain, generating domain-specific sub-functions from the domain-specific functions according to a hierarchical mapping, generating H-Tokens, each encapsulating one of a domain-specific function or a domain-specific sub-function and relationships domain-specific functions and the domain-specific sub-functions, implementing the of H-Tokens, assembling a response using the implemented of H-Tokens, and transmitting the response to the user.

Abstract: Systems and methods are directed to minimizing hallucinations in a generated summary. A summary generation system embodied within a server triggers a large language model (LLM) to generate an initial summary for a subject. Based on the initial summary, the server prompts the LLM to generate a list of factual questions about the initial summary. The server then triggers the LLM to answer the list of factual questions without knowledge of the initial summary and using internal knowledge of the LLM. Questions from the list of factual questions that received a positive answer are identified. Based on the questions, the server prompts the LLM to generate a refined summary from the initial summary. The server then generates a user interface that presents the refined summary. Approval of the refined summary triggers generation of a publication using the refined summary.

Abstract: Certain aspects of the disclosure provide a method for generating a final output response. The method may include receiving an input; generating a plurality of intermediate responses to the input using a plurality of machine learning models, wherein each machine learning model of the plurality of machine learning models generates at least one intermediate response based on the input; generating a semantic consistency metric for each respective intermediate response of the plurality of intermediate responses by performing a comparison between the respective intermediate response and other intermediate responses of the plurality of intermediate responses; selecting a subset of the plurality of intermediate responses based on the semantic consistency metric of each respective intermediate response of the plurality of intermediate responses; and generating a final output response based on the subset of the plurality of intermediate responses.

Abstract: This disclosure relates to a conversation method, an apparatus, an electronic device, a storage medium, and a product, which relates to the field of artificial intelligence technology. The conversation method includes: displaying a first conversation between a first user and a second user on a client of the first user, calling one or more robots for the first user based on information of the first conversation; generating auxiliary conversation information of the robots based on the first conversation; and displaying the auxiliary conversation information.

Abstract: Various example embodiments described herein provide for systems, methods, devices, instructions, and the like for suffix-based speculative token decoding for an artificial intelligence model, such as a language model (e.g., large language model). In particular, some example embodiments provide an AI model system with hybrid speculative token decoding, which combines suffix-based speculative token decoding with a draft AI model approach to speculative token decoding. With this hybrid decoding approach, various example embodiments can accelerate inference throughput while adapting to different types of workloads, particularly agentic applications that exhibit repetitive token generation patterns.

Abstract: A semantic identifier that represents information within a document may be determined by training a language model or other machine learning model using a self-supervised process. The model encodes text to generate an embedding. A decoder determines a semantic identifier token that represents information in the text based on the embedding and a previous semantic identifier token if present. The identifier determined by the decoder is aligned with one of a selected set of semantic identifiers indicated in codebook data. To determine the accuracy of the semantic identifier token, a second decoder is used to attempt to reconstruct the original text using the semantic identifier token and a portion of the original text. Differences between the reconstructed text and the original text are used to determine a loss value, and the parameters of the machine learning model or the codebook data are trained based on minimizing the loss value.

Abstract: The present disclosure refers to a data processing and retrieval method for dynamically assessing materiality of a signal. A method comprises receiving a list containing a plurality of entities of interest and a plurality of features of interest. Additionally, a plurality of documents containing text describing the features of interest related to the entities of interest can be provided. The method then measures performance of the entities of interest relative to the features of interest.

Abstract: An information processing system characterized by comprising: a response data generation unit that generates response data with which a character responds in response to conversation data from a user to the character, wherein the response data generation unit generates the response data so as to quote lines included in an original work in which the character appears; and an output unit that outputs the response data to the user.

Abstract: A system and method for querying data sources for cybersecurity analysis is presented. The method includes identifying, by a device, fields of security logs that are relevant to a natural language query; computing, by the device, values for the identified fields based on actual values contained in the identified fields; refining, by the device, a schema of the security logs to include the identified fields and the computed values; generating, based on at least the refined schema, a prompt for a Large Language Model (LLM), wherein the LLM is executed by an AI system; feeding the prompt to the LLM, wherein the LLM executes the prompt using the AI system, to convert the natural language query into a Kusto Query Language (KQL) query; and generating a KQL query that is executed on at least one target data source.

Abstract: A document analysis and processing (DAP) system is disclosed that includes at least one memory configured to store a corpus of documents and a topic classifier having a first trained artificial intelligence (AI) model and at least one processor configured to execute stored instructions to perform actions. The actions include, for each document of the corpus of documents: using the first trained AI model of the topic classifier to identify topics of each page of the document; mapping each of the identified topics of each page of the document to respective topic colors; combining the respective topic colors of each page of the document to yield a respective page color code for each page of the document; and combining the respective page color code of each page of the document to yield a respective document color code of the document.

Abstract: An information learning apparatus includes a processing circuitry. The processing circuitry is configured to: acquire text information and field information included in the text information; calculate a field loss based on the text information and the field information; and store parameters of a trained model, and updating the parameters of the model based on the field loss.

Abstract: Enumerated source text passages may be determined based on one or more source text documents. The enumerated source text passages may include source text passage identifiers uniquely identifying the passages. A novel text passage including novel text portions may be determined based on a query and the enumerated source text passages. One or more of the novel text portions may be verified by a large language model to produce text verification information. A novel text generation message including novel text generated by the large language model may be determined based on the text verification information and sent to a client machine.