公开(公告)号：US20250094556A1

公开(公告)日：2025-03-20

申请号：US18368274

申请日：2023-09-14

Applicant: Google LLC

Inventor： Obaid Sarvana

IPC: G06F21/36

Abstract: A method for using authentication challenges to automatically obtain training data to train a machine learning model (MLM). The method includes identifying a generative MLM to be trained using training data reflecting analytical responses of humans, and automatically collecting the training data from a plurality of users by providing an authentication challenge for each user attempting to access a resource. The authentication challenge requests a set of responses from a respective user of the plurality of users. The set of responses include a first response to a first sample which indicates whether the respective user is a human, and a second response to a second sample which indicates an analytical response of the respective user. Responsive to determining that the respective user is a human, the second response is used as part of the training data for the generative MLM.

公开(公告)号：US20250086405A1

公开(公告)日：2025-03-13

申请号：US18481803

申请日：2023-10-05

Applicant: GOOGLE LLC

Inventor： Swaroop Mishra ,  Ragha Kotikalapudi ,  Obaid Sarvana ,  Sahitya Potluri ,  YaGuang Li ,  Taylor Bos ,  Steven Zheng ,  Hanzhao Lin ,  Chenkai Kuang ,  Heng-Tze Cheng ,  Ed H. Chi ,  Quoc Le

IPC: G06F40/40 ,  G06N3/08

Abstract: Some implementations relate to generating a training and/or evaluation dataset with LLM prompts (e.g., derived from user queries) based on a prompt complexity. An input prompt, for example derived from a user query, is received. The input prompt is decomposed into a prompt tree comprising a plurality of nodes. The plurality of nodes comprise: a plurality of leaf nodes corresponding to simple sub-prompts of the input query; a plurality of branch nodes of sub-prompts each corresponding to multiple simple sub-prompts; and a root node corresponding to the input prompt. A prompt complexity is determined based on a path length of the prompt tree. The prompt complexity is compared to a threshold complexity. If the prompt complexity is above the threshold complexity, the input prompt is included in a set of training prompts and/or a set of evaluation prompts.