公开(公告)号：US20250165721A1

公开(公告)日：2025-05-22

申请号：US18515246

申请日：2023-11-20

Applicant: Microsoft Technology Licensing, LLC

Inventor： Roy EISENSTADT ,  Abed El Kader ASI ,  Bar SEGAL ,  Eyal ZACH ,  Royi RONEN

IPC: G06F40/40 ,  G06F40/103

Abstract: Example solutions for reducing the likelihood of hallucinations by large language models (LLMs) and improving the relevance of generated text are disclosed. A set of multiple of machine learning (ML) models, each custom-trained to identify a different specific topic within text, dynamically generate multiple topic-specific prompts from a received email in an email thread. A user, responding to the prompts, produces material that is used in conjunction with customer relations management (CRM) data and enterprise suite data (e.g., calendar/schedule information) to dynamically generate an LLM prompt. An LLM, using the prompt, generates output text suitable for a business correspondence, such as a reply email, to the sender of the email. The combination of the responses to the multiple topic-specific prompts and the CRM and enterprise suite data in the LLM prompt both ensures relevance of the reply correspondence and minimizes the risk of hallucinations.