Abstract: The present teaching relates to adaptive generative AI via feedback. Human evaluators evaluate an answer automatically generated by a machine expert in response to a question based on a reference from a source. The evaluation is relied on to update a fidelity metric for each human evaluator. A cumulative ranking of the answer is determined using the evaluation and the updated fidelity metric of each human evaluator. A fidelity attribute for the machine expert is updated based on the cumulative ranking. Feedback is created based on the answer, the question, the cumulative ranking, and the updated fidelity attribute for adapting the performance of the Q&A system.

Abstract: The present teaching relates to a Q&A framework for quality controlling of automatically generated answers via AI. Based on a question on a subject matter received from a user, at least one machine expert is selected to answer the question based on past performances of multiple machine experts for generating respective candidate answers to the question. Each selected machine expert creates a candidate answer based on a reference from a source. Quality assessment is performed with respect to each candidate answer from a respective machine expert and is relied on to determine a candidate answer as the answer to the question. Such determined answer is provided to the user as a response to the question.

Abstract: A user device may receive a web page having multiple different types of content (e.g., text, images, videos, etc.). The user device may identify the different types of content, and may generate reformatted pages that each include a particular type of content associated with the web page. For instance, one reformatted page may include text content of the web page, without including image content of the web page (and/or vice versa). The reformatted pages may include resized and/or repositioned versions of the original content (e.g., resized and/or reformatted images and/or text).

Abstract: A user device may receive a web page having multiple different types of content (e.g., text, images, videos, etc.). The user device may identify the different types of content, and may generate reformatted pages that each include a particular type of content associated with the web page. For instance, one reformatted page may include text content of the web page, without including image content of the web page (and/or vice versa). The reformatted pages may include resized and/or repositioned versions of the original content (e.g., resized and/or reformatted images and/or text).

Abstract: A mobile device, such as a smart phone, receives program instructions, such as program instructions to evaluate components and/or software in the mobile device. The mobile device detects a local network and determines whether an attribute of the local network matches a desired attribute, such as a service set identifier (SSID) identified in the program instructions. When the attribute of the local network matches the desired attribute, the mobile device executes the program instructions. If the attribute of the local network does not match the desired attribute, the mobile device continues to look for a matching local network before executing the program instructions.

Abstract: A mobile device, such as a smart phone, receives program instructions, such as program instructions to evaluate components and/or software in the mobile device. The mobile device detects a local network and determines whether an attribute of the local network matches a desired attribute, such as a service set identifier (SSID) identified in the program instructions. When the attribute of the local network matches the desired attribute, the mobile device executes the program instructions. If the attribute of the local network does not match the desired attribute, the mobile device continues to look for a matching local network before executing the program instructions.