公开(公告)号：US20250133037A1

公开(公告)日：2025-04-24

申请号：US18920765

申请日：2024-10-18

Applicant: Maplebear Inc.

Inventor： Jacob Jensen ,  Shubhanshu Mishra ,  Aomin Wu ,  Rajpal Paryani ,  Guanghua Shu ,  Sicheng Zhou

IPC: H04L51/02

Abstract: A system may smartly edit the context of a conversation to be input into a chatbot LLM by using a conversation compression algorithm to prune and compress redundant elements. The system evaluates the conversation context compression algorithm using both a chatbot LLM and an adversarial LLM. The system retrieves a logged conversation and generates a compressed conversation context from the logged conversation. The system generates a synthetic user response by applying the adversarial LLM and generates a test conversation by replacing a user response in the conversation with the synthetic user response. The system generates a compressed context of the test conversation. The system generates a test chatbot LLM response by prompting the chatbot LLM with the compressed context of the test conversation. The system evaluates the conversation context compression algorithm by comparing the test chatbot response with a benchmark chatbot response.

公开(公告)号：US20240303710A1

公开(公告)日：2024-09-12

申请号：US18596590

申请日：2024-03-05

Applicant: Maplebear Inc.

Inventor： Li Tan ,  Haixun Wang ,  Shishir Kumar Prasad ,  Tejaswi Tenneti ,  Aomin Wu ,  Jagannath Putrevu

IPC: G06Q30/0601 ,  G06Q30/0201 ,  G06Q30/0282

CPC classification number: G06Q30/0627 ,  G06Q30/0201 ,  G06Q30/0282

Abstract: A system, for example, an online system uses a machine learning based language model, for example, a large language model (LLM) to process crowd-sourced information provided by users. The crowd-sourced information may include comments from users represented as unstructured text. The system further receives queries from users and answers the queries based on the crowd-sourced information collected by the system. The system generates a prompt for input to a machine-learned language model based on the query. The system provides the prompt to the machine-learned language model for execution and receives a response from the machine-learned language model. The response comprises the insight on the topic and evidence for the insight. The evidence identifies one or more comments used to obtain the insight.