Abstract: An example method includes providing, to a sequence model (i) a plurality of few-shot prompts, wherein each prompt comprises a demonstration passage, a demonstration task, and a demonstration query, wherein the demonstration task describes a type of retrieval, and wherein the demonstration query is relevant to the demonstration task, and (ii) a plurality of passages sampled from a corpus of passages. The method also includes receiving, from the sequence model and for the plurality of passages and based on the plurality of few-shot prompts, a respective plurality of predicted task-query pairs, the sequence model having been prompted to predict a task based on an input passage, and predict an output query relevant to the predicted task. The method further includes generating a synthetic training dataset comprising the plurality of passages and the respective plurality of predicted task-query pairs. The method also includes providing the synthetic training dataset.

Abstract: A method and a light detector that includes (i) a photon to electron converter a photon to one or more photoelectrons; (ii) a photoelectron detection circuit that includes a photoelectron sensing region; (iii) a chamber; (iv) a bias circuit that is configured to supply to the light detector one or more biasing signals for accelerating a propagation of the one or more photoelectrons within the chamber and towards the photoelectron sensing region; (iv) a photoelectron manipulator that is configured to operate in a selected operational mode out of multiple operational modes that differ by their level of blocking, (v) a controller that is configured to control the photoelectron manipulator based on a feedback about the at least one of (a) the photon, (b) the one or more photoelectrons, (c) a previous photon and, (d) previous one or more photoelectrons.