Abstract: A method, apparatus, non-transitory computer readable medium, and system for document retrieval include obtaining a query and a document. A prompt generator generates a prompt for a reasoning model based on the query and the document. The reasoning model generates a reasoning result based on the prompt. In some cases, the reasoning result indicates that the document answers the query. A machine learning model provides the document in response to the query based on the reasoning result.

Abstract: Methods and systems are provided for using generative artificial intelligence to evaluate fine-tuned language models. In embodiments described herein, natural language text snippets are generated via a generative language model based on corresponding data. A language model is fine-tuned into a fine-tuned language model via a language model fine-tuning component using the natural language text snippets and the corresponding data as training data. Independent natural language text snippets are generated via the generative language model based on the corresponding data. Each independent natural language text snippet is different than each corresponding natural language text snippet. An evaluation metric of the fine-tuned language model is generated via an evaluation component based on the independent natural language text snippets and the corresponding data.

Abstract: Methods and systems are provided for hallucination prevention for natural language insights. In embodiments described herein, a template-based insight with a set of facts is generated by a template-based insights engine. The set of facts are generated from a set of data and the template-based insight is generated based on a text template. A natural language insight is generated from the template-based insight through a language model. If a threshold number of facts of the template-based insight are missing from the natural language insight as determined by a hallucination gatekeeper engine then a new natural language insight is generated from the template-based insight through the language model.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating naturally phrased insights about data charts using light language models distilled from large language models. To synthesize training data for the light language model, in some embodiments, the disclosed systems leverage insight templates for prompting a large language model for generating naturally phrased insights. In some embodiments, the disclosed systems anonymize and augment the synthesized training data to improve the accuracy and robustness of model predictions. For example, the disclosed systems anonymize training data by injecting noise into data charts before prompting the large language model for generating naturally phrased insights from insight templates. In some embodiments, the disclosed systems further augment the (anonymized) training data by splitting or partitioning data charts into folds that act as individual data charts.

Abstract: Systems and methods for natural language processing are described. Embodiments of the present disclosure obtain a chart and a query via a user interface. An answer model generates an answer to the query based on the chart, wherein the answer model comprises a machine learning model trained based on chart data for the chart. A description model generates a visual description based on the answer and the chart, wherein the description model comprises a machine learning model trained based on a chart specification for the chart. A response component transmits a response to the query based on the answer and the visual description.

Abstract: Systems and methods for image searching are described. The systems and methods include receiving a search query comprising user input for a reference image; converting the user input for the reference image to a preference statement using a machine learning model; encoding the preference statement in an embedding space to obtain an encoded preference statement; combining the encoded preference statement with an encoded reference image representing the reference image in the embedding space to obtain a multi-modal search encoding; and performing a search operation using the multi-modal search encoding to retrieve a second image, wherein the second image differs from the reference image based on the user input for the reference image.