Abstract: A method, a system, and a computer program product for tuning a large language model. One or more first electronic documents are sampled to generate one or more sampled electronic documents. One or more portions of one or more second electronic documents are identified and extracted from the second electronic documents. The sampled electronic documents are sent to a generative artificial intelligence (AI) model to generate one or more first labels. One or more portions of the second electronic documents are sent to the generative AI model to generate one or more second labels. A large language model is trained using one or more first labels and one or more second labels to generate a trained large language model.

Abstract: A system for an electronic document that includes one or more electronic components comprising: natural language content; and a programmable component that comprises computer executable instructions that define: one or more state objects that indicate compliance with the natural language content, wherein a state object comprises a state variable; and logic that programmatically change, based on an application programming interface input, one or more state variables indicating a compliance event effect of the programmable component; an indication of one or more application programming inputs configured to cause execution, based on an input message from an external computing resource, of at least one programmable component of the one or more electronic component; and an indication of one or more contract outputs configured to indicate a value of at least one state variable to an external computing resource.

Abstract: A system for generating counterparty profiles for electronic agreements, based on an indication of a change to a pending clause of an electronic agreement, may determine, based on a second entity, a first historical document and a second historical document. The system may correlate the pending clause of the electronic agreement with a first clause of a plurality of first clauses of the first historical document and with a second clause of a plurality of second clauses of the second historical document based on first content of the first clause and second content of the second clause. Based on the correlation, the system may generate difference information between the first content of the first clause and the second content of the second clause. The system may generate a counterparty profile for the second entity based on the difference information.

Abstract: A method, a system, and a computer program product for generating and using an identifier data model. A first identifier in a plurality of identifiers is assigned to a first version in a plurality of versions of an electronic document processed by a computing system in a plurality of computing systems. A second identifier assigned to a second version the electronic document by the second computing system is received. The second computing system generates the second version of the electronic document by processing the electronic document and assigns the second identifier to the second version of the electronic document. A data model mapping the second identifier to the first identifier is generated and stored. Each identifier included in the data model is associated with a version of the electronic document processed by a computing system in the plurality of computing systems.

Abstract: A method, a system, and a computer program product for generating and capturing/certifying an interface embedding an electronic document. An electronic document and one or more presentation parameters associated with presentation of the electronic document on a graphical user interface are received. One or more electronic interfaces embedding the electronic document are generated. The electronic interfaces may capture the electronic document in accordance with one or more presentation parameters. One or more electronic interfaces are presented on the graphical user interface with the electronic document embedded in the electronic interfaces. The captured electronic document is stored in one or more storage locations.

Abstract: A document execution engine receives a training set of data including training documents that each include one or more passages associated with a passage type and a level of risk. The document execution engine trains a machine learned model based on the training set. The trained machine learned model, when applied to subsequently identified passages within documents in the document execution environment, can identify a passage with above threshold levels of risk (e.g., a high-risk passage) based on a passage type of the passage. The trained machine learned model can then provide for display the high-risk passage and a related passage of the same passage type from a second document within the document execution environment to the user via a document passage comparison interface. Differences between the passages can be highlighted, enabling a user to quickly compare and contrast the passages.

Abstract: A system, for example, a document management system stores documents and manages workflows associated with documents. The document management system allows discovery of templates based on explicit searches performed by users or automatic searches performed based on a context. The document management system allows generating new document templates based on selected versions of document component templates. The generated document template may be stored as a new version. The document management system instantiates documents based on templates by predicting values of variables used in the template based on various factors that describe the context in which the template is being used. The values used for instantiating variables may be generated using machine learning models that may be trained using historical data stored in the document management system.

Abstract: Through a workflow interface, a document management system enables a user to establish a document workflow. The document workflow establishes a set of document actions for the document management system to perform automatically in response to a request from the user. The user defines the document workflow by selecting from a set of workflow operations and specifying parameters for the selected workflow operation. The user additionally defines an approval workflow operation and a rejection workflow operation that designate document actions in the event that a document is approved or rejected, respectively. The document management system performs at least a portion of the document workflow in an order determined from the workflow interface.

Abstract: A document management system generates a form interface including fields that correspond to a set of document tags selected by a user. The document tags, each of which corresponds to a document term, is located in a document template. The document management system suggests fields corresponding to document terms not selected by the user, but often included in similar document templates. In response to the user's selection of at least one of the suggested fields, the document management system modifies the form interface to include the selected suggested field. After the fields in the form are completed, thus defining the document terms, the document management system generates a document with each of the terms in place of the document tags.

Abstract: A method, a system, and a computer program product for summarizing an electronic document. A structural representation of the document is generated and/or received. The structural representation specifies one or more elements of the document and one or more relationships between one or more elements of the document. A machine learning model is identified for the document. The model is applied, based on the structural representation, to one or more portions of the document to generate a hierarchical representation for the portions. A request to execute at least one processing task related to the document is received. At least one generated hierarchical representation of at least one portion of the document is sent to a generative artificial intelligence model to execute the processing task by generating a response to the request. The response is and presented on a graphical user interface of a user computing device.

Abstract: A document execution engine receives a training set of data including training documents that each include one or more passages associated with a passage type and a level of risk. The document execution engine trains a machine learned model based on the training set. The trained machine learned model, when applied to subsequently identified passages within documents in the document execution environment, can identify a passage with above threshold levels of risk (e.g., a high-risk passage) based on a passage type of the passage. The trained machine learned model can then provide for display the high-risk passage and a related passage of the same passage type from a second document within the document execution environment to the user via a document passage comparison interface. Differences between the passages can be highlighted, enabling a user to quickly compare and contrast the passages.

Abstract: A method, a system, and a computer program product for connecting computing systems. A connection request to connect with one or more computing systems is received. Based on the connection request, at least one computing system in one or more computing systems is identified. The computing system is identified based on one or more tasks associated with the connection request and to be performed using the computing system. A connection interface for connection with the computing system is dynamically generated. The connection interface is generated using a connection data model associated with the computing system. Connection, using the connection interface to the computing system, is formed, and one or more tasks is executed using the connection interface.

Abstract: Techniques for an artificial intelligence (AI) platform to search a document collection are described. Embodiments may use AI and machine learning techniques within a framework of an electronic document management system to perform semantic searching of an electronic document or a collection of electronic documents for certain types of information. The AI platform may summarize the information in a natural language representation of a human language. Other embodiments are described and claimed.

Abstract: A method, a system, and a computer program product for determining renewal of agreement documents. A first machine learning model is used to generate one or more portions of a document. Each portion of the document is associated with a predetermined subject. A query is generated using the predetermined subject. The query and one or more definitions of one or more attributes are provided to a second machine learning model. At least one attribute and a value assigned to the attribute are received from the second machine learning model. The value is extracted from one or more portions and assigned to the attribute. A graphical user interface displaying the attribute and the value assigned to the attribute is generated.

Abstract: Techniques for an artificial intelligence (AI) platform to manage a document collection are described. Embodiments may use AI and machine learning techniques within a framework of an electronic document management system to manage and mine a collection of electronic documents for certain types of information. The information may be analyzed and used to generate insights for a defined entity. The insights may comprise deviations, modifications or changes made to an electronic document within the electronic document management system. Other embodiments are described and claimed.

Abstract: A document management system can include an artificial intelligence-based document manager that can perform one or more predictive operations based on characteristics of a user, a document, a user account, or historical document activity. For instance, the document management system can apply a machine-learning model to determine how long an expiring agreement document is likely to take to renegotiate and can prompt a user to begin the renegotiation process in advance. The document management system can detect a change to language in a particular clause type and can prompt a user to update other documents that include the clause type to include the change. The document management system can determine a type of a document being worked on and can identify one or more actions that a corresponding user may want to take using a machine-learning model trained on similar documents and similar users.

Abstract: Techniques for artificial intelligence (AI) custom fields are described. A method comprises receiving a custom rule comprising a query request for information in an electronic document stored in a data repository, generating a vectorized rule from the custom rule, selecting a subset of vectorized portions from a set of vectorized portions of the electronic document stored in a vector database corresponding to the vectorized rule, sending the vectorized rule and the subset of vectorized portions to a machine learning (ML) model, receiving a query response to the query request from the ML model, the query response comprising a summary of information contained within one or more vectorized portions of the subset of vectorized portions or a comment on the information contained within the one or more vectorized portions. Other embodiments are described and claimed.

Abstract: A method, a system, and a computer program product for content-based document access. A content of an electronic document is analyzed using a machine learning (ML) model. The ML model determines presence of a plurality sensitive data in the document. One or more document entity-based parameters are received. At least one sensitive data in the plurality of sensitive data is identified. At least one recipient computing device in a plurality of computing devices is prevented from receiving the document containing at least one sensitive data. The sensitive data is extracted from the document. The document is modified to redact the sensitive data and a modified electronic document is generated. The modified electronic document is transmitted to at least one recipient computing device.

Abstract: A method, a system, and a computer program product for federated document learning. A plurality of representations of a plurality of datasets from a plurality of client systems are received. Each representation corresponds to a dataset associated with a client system and is generated using a first machine learning (ML) model. A second ML model is applied to the plurality of representations to generate a combined representation of the plurality of datasets. Data from each dataset is not provided to the second ML model. The combined representation is filtered using one or more filtering parameters to generate a filtered representation. Using the second ML model, one or more model weights for training a third ML model in a plurality of third ML models are generated. Each third ML model is associated with a respective client system. The model weights are provided to the plurality of third ML models.

Abstract: A method, a system, and a computer program product for generating a benchmarking dataset. A type of an electronic document is determined. Using the type of the electronic document, a first request to generate one or more labels for the electronic document is generated. Using a content of the electronic document, a second request to generate one or more labels for the electronic document is generated. The electronic document and the first and second requests are sent to a generative artificial intelligence (AI) model. The generative AI model generates one or more first labels for the electronic document based on the first request and one or more second labels for the electronic document based on the second request. Using one or more first and second labels, one or more labels for the electronic document are generated.