Abstract: A computer implemented method transforms data. Responsive to receiving a data transformation of an input string to an output string, a computer system identifies mappable tokens in the input string that are mappable to the output string. The computer system creates a set of initial mappings for a set of common tokens in the mappable tokens. The set of initial mappings maps the set of common tokens from the input string to the output string. The computer system creates a set of user mappings that maps the mappable tokens from input string to the output string using a user input to the set of initial mappings. The computer system generates program code that transform input strings to output strings using the set of user mappings that maps the mappable tokens from input string to the output string, wherein the program code is used to transform input strings to output strings.

Abstract: A method, computer program, and computer system are provided for online fairness monitoring. A dataset having one or more entries with one or more protected attributes and data corresponding to a trained machine learning model is received. An entry having a maximum reward is selected based on a reward probability associated with the entry. A determination is made as to whether bias has developed in the trained machine learning model toward one or more of the one or more protected attributes based on a change to the reward probability or a distribution of reward probabilities exceeding a threshold value.

Abstract: An example operation may include one or more of identifying an external system that passes an input attribute to a process based on a workflow representation of the process, building a simulator of the external system based on attributes of the external system identified from the workflow representation, simulating future values of the input attribute to be passed to the process by the external system based on the simulator of the external system and a previous simulation run of the process performed via a workflow software application, and executing a new simulation of the process via the workflow software application based on the simulated future values of the input attribute.

Abstract: A computer implemented method transforms data. Responsive to receiving a data transformation of an input string to an output string, a computer system identifies mappable tokens in the input string that are mappable to the output string. The computer system creates a set of initial mappings for a set of common tokens in the mappable tokens. The set of initial mappings maps the set of common tokens from the input string to the output string. The computer system creates a set of user mappings that maps the mappable tokens from input string to the output string using a user input to the set of initial mappings. The computer system generates program code that transform input strings to output strings using the set of user mappings that maps the mappable tokens from input string to the output string, wherein the program code is used to transform input strings to output strings.

Abstract: Methods, systems, and computer program products for automatically modifying responses from generative models using artificial intelligence techniques are provided herein. A computer-implemented method includes obtaining data pertaining to at least one conversation involving at least one automated conversation exchange software program and at least one user; identifying, among words proposed by the at least one automated conversation exchange software program in connection with the at least one conversation, words qualifying as belonging to one or more predetermined categories by processing the obtained data using artificial intelligence techniques; determining, by processing the identified words and at least one word-based data source, one or more alternate words; modifying at least a portion of the proposed words by replacing at least a portion of the identified words with at least a portion of the one or more alternate words; and performing at least one automated action based on the modifying.

Abstract: Methods, systems, and computer program products for adjusting machine learning models based on simulated fairness impact are provided herein. A computer-implemented method includes obtaining, by a central simulation system, policies to be used for performing a simulation involving machine learning models, implemented on different systems, interacting with a target population; providing information for configuring simulators on the different systems, each simulator representing at least the machine learning model of a given one of the different systems; performing iterations of the simulation for the policies, wherein, for each iteration, the central simulation system: predicts a state of the target population, provides the state to the simulators, and collects metrics based on results of the simulators; and selecting and sending one of the policies to at least one of the different systems based on the collected metrics.

Abstract: Methods, systems, and computer program products for automated fairness-driven graph node label classification are provided herein. A computer-implemented method includes obtaining at least one input graph; predicting one or more node labels associated with the at least one input graph by processing at least a portion of the at least one input graph using a graph node label prediction model, wherein the graph node label prediction model includes at least one loss function; generating an updated version of the graph node label prediction model based at least in part on the one or more predicted node labels and one or more group fairness-based constraints relevant to the at least one input graph; and performing one or more automated actions using the updated version of the graph node label prediction model.

Abstract: A computer implemented method, computer system, and computer program product for transforming mapped data fields of enterprise applications. A number of processor units receiving a matching from a source data field to a target data field. The set of processor units receiving a number of annotated examples of transformations from a source format to a target format. Based on the annotated examples, the set of processor units autogenerating a query language expression for transforming data items from the source format to the target format.

Abstract: Methods, systems, and computer program products for determining data representative of bias within a model are provided herein. A computer-implemented method includes obtaining a first dataset on which a model was trained, wherein the first dataset contains protected attributes, and a second dataset on which the model was trained, wherein the protected attributes have been removed from the second dataset; identifying, for each of the one or more protected attributes in the first dataset, one or more attributes in the second dataset correlated therewith; determining bias among at least a portion of the identified correlated attributes; and outputting, to at least one user, identifying information pertaining to the one or more instances of bias.

Abstract: Methods, systems, and computer program products for automatically improving data annotations by processing annotation properties and user feedback are provided herein. A computer-implemented method includes obtaining data annotation pairs, each comprising an input data annotation in a first format and a corresponding output data annotation in a second format; determining, within at least a portion of the data annotation pairs, one or more non-diffs; identifying, across the at least a portion of data annotation pairs, data annotation properties associated with multiple intents by processing the non-diffs using property-related rules; modifying at least a portion of the data annotation pairs based on the identified data annotation properties; outputting the modified data annotation pairs to at least one user; and generating a final collection of data annotation pairs by processing at least a portion of the modified data annotation pairs and user feedback received in response to the outputting.

Abstract: One embodiment provides a method, including: receiving a dataset and a model corresponding to a bias checker, wherein the bias checker detects bias within both the dataset and the model, based upon a bias checking algorithm and a bias checking policy, wherein the dataset comprises a plurality of attributes; testing the bias checking algorithm of the bias checker by (i) generating test cases that modify the dataset by introducing bias therein and (ii) running the bias checker against the modified dataset; testing the bias checking policy of the bias checker by generating a plurality of test cases and running the bias checker against the plurality of test cases; and providing a notification to a user regarding whether the bias checker failed to indicate bias for one or more of the plurality of attributes.

Abstract: One embodiment provides a method, including: receiving a target unstructured document for determining whether the target unstructured document comprises biased information; identifying an objective of the target unstructured document by extracting, from the target unstructured document, (i) entities and (ii) relationships between the entities; creating a structured knowledge base, wherein the creating comprises (i) creating an entry in the structured knowledge base corresponding to the target unstructured document, (ii) identifying other unstructured documents having a similarity to the target unstructured document, and (iii) generating an entry in the structured knowledge base corresponding to each of the other unstructured documents; applying a bias detection technique on the structured knowledge base; and providing an indication of whether the target unstructured document comprises bias.

Abstract: A method, computer system, and a computer program product for generating deep learning model insights using provenance data is provided. Embodiments of the present invention may include collecting provenance data. Embodiments of the present invention may include generating model insights based on the collected provenance data. Embodiments of the present invention may include generating a training model based on the generated model insights. Embodiments of the present invention may include reducing the training model size. Embodiments of the present invention may include creating a final trained model.

Abstract: Methods, systems, and computer program products for generating explanations for a semantic parser are provided herein. A computer-implemented method includes providing to a generative model (i) at least one query and (ii) a context of at least one dataset applicable to the at least one query, wherein the generative model generates a plurality of perturbations for the at least one input query based on the context; providing the plurality of perturbations as inputs to a context aware sequence-to-sequence model, thereby obtaining a plurality of outputs; and generating, for (i) an additional query provided as input to the context aware sequence-to-sequence model and (ii) a context applicable to the additional query, an explanation indicative of one or more parts of the additional query that contributes to an output corresponding to the additional query, based at least in part on the plurality of outputs corresponding to the perturbations.

Abstract: A method for blockchain certification of artificial intelligence factsheets that includes receiving by a computing device, an artificial intelligence model. The computing device generates an artificial intelligence factsheet based upon logic of the artificial intelligence model. The computing device generates a blockchain link for a blockchain. The blockchain link certifies the artificial intelligence factsheet. The computing device transmits the blockchain link certifying the artificial intelligence factsheet to other computing devices.

Abstract: Methods, systems, and computer program products for detecting contextual bias in text are provided herein. A computer-implemented method includes identifying, by a machine learning network, a protected attribute in one or more data samples; processing the identified data samples using a first sub-network of the machine learning network, wherein the first sub-network is configured to determine a plurality of contexts of the protected attribute across the identified data samples; determining an impact of each of the plurality of contexts on a second sub-network of the machine learning network, wherein the second sub-network of the machine learning network is configured to classify a given data sample into one of a plurality of classes; and adjusting the second sub-network of the machine learning to account for the impact of at least one of the plurality of contexts on the second sub-network.

Abstract: A source of bias identification (SoBI) tool is provided that identifies sources of bias in a dataset. A bias detection operation is performed on results of a computer model, based on an input dataset, to generate groupings of values for a protected attribute corresponding to a detected bias in the operation of the computer model. The SoBI tool generates a plurality of sub-groups for each grouping of values. Each sub-group comprises an individual value, or a sub-range, for the protected attribute. The SoBI tool analyzes each of the sub-groups in the plurality of sub-groups, based on at least one source of bias identification criterion, to identify one or more sources of bias in the input dataset. The SoBI tool outputs a bias notification to an authorized computing device specifying the one or more sources of bias in the input dataset.

Abstract: Methods, systems, and computer program products for improving trustworthiness of artificial intelligence models in presence of anomalous data are provided herein. A method includes obtaining a machine learning model and a set of training data; determining one or more anomalous data points in said set of training data; for a given one of said anomalous data points, identifying attributes that decrease confidence with respect to at least one output of said machine learning model; determining that a root cause of said decreased confidence corresponds to one of: a class imbalance issue related to said at least one attribute, a confused class issue related to said at least one attribute, a low density issue related to said at least one attribute, and an adversarial issue related to said at least one attribute; and performing step(s) to improve said confidence based at least in part on said determined root cause.

Abstract: Methods, systems, and computer program products for automatically modifying responses from generative models using artificial intelligence techniques are provided herein. A computer-implemented method includes obtaining data pertaining to at least one conversation involving at least one automated conversation exchange software program and at least one user; identifying, among words proposed by the at least one automated conversation exchange software program in connection with the at least one conversation, words qualifying as belonging to one or more predetermined categories by processing the obtained data using artificial intelligence techniques; determining, by processing the identified words and at least one word-based data source, one or more alternate words; modifying at least a portion of the proposed words by replacing at least a portion of the identified words with at least a portion of the one or more alternate words; and performing at least one automated action based on the modifying.

Abstract: Methods, systems, and computer program products for priority-based, accuracy-controlled individual fairness of unstructured text are provided herein. A method includes identifying one or more samples in a set of data used to train a machine learning model having at least one attribute; generating counterfactual samples for each of the one or more identified samples; calculating scores for the one or more identified samples based at least in part on output of the machine learning model with respect to the counterfactual samples, wherein the scores indicate a relative level of bias between the one or more identified samples corresponding to the at least one attribute; creating an enhanced set of data at least in part by supplementing at least a portion of the identified samples with the corresponding counterfactual samples based on the calculated scores; and training the machine learning model using the enhanced set of data.