IP Library › Granted Patent US 12,462,095
Granted Patent B2
US 12,462,095 · App. 18/299,842 · Granted Nov 4, 2025

Dynamic construction of large language model prompts

Inventors: Abed El Kader Asi (Sammamish, WA); Alexander Tsvetkov (Tel Aviv, IL); Royi Ronen (Tel Aviv, IL); Yarin Kuper (Tel Aviv, IL); Shahar Zvi Keren (Hemed, IL); Roy Eisenstadt (Tel Aviv, IL)
Assignee: Microsoft Technology Licensing, LLC
G06F40/166G06F40/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,462,095
App. No.
18/299,842
Granted
Nov 4, 2025
Kind
B2
Abstract

Example solutions for reducing the likelihood of hallucinations by language models, such as large language models (LLMs) are disclosed. By injecting a sufficient range and quantity of curated factual data into a prompt, the likelihood of a hallucination by an LLM may be reduced. This enables language models to be used in a wider range of settings, in which fabrication of facts is problematic, while reducing the need for a human to carefully check the generated text for accuracy. Examples include: generating a summary of a transcript using a summarization model; extracting topic-specific data from stored data using a scoring model; dynamically generating a language model prompt using the topic-specific data and the summary; and generating an output text using a language model and the language model prompt.

Claims (40)

1 . A system comprising:

a processor; and

a computer-readable medium storing instructions that are operative upon execution by the processor to:

receiving a transcript of a conversation between participants;

generate a summary of the transcript using a summarization model, the summary relating to a topic of the conversation;

extract topic-specific data associated with the topic from a customer relations management (CRM) or enterprise suite data set using a scoring model, the CRM or enterprise data set excluding the transcript;

dynamically generate a large language model (LLM) prompt based on the summary by resolving a difference between the topic-specific data and the summary in favor of the topic-specific data; and

generate, by an LLM model, an output text based on the LLM prompt.

2 . The system of claim 1 , wherein the instructions are further operative to:

transmit, across a computer network, the output text as an electronic mail (email) message.

3 . The system of claim 1 , wherein the topic of the conversation comprises an action item extracted from the transcript.

4 . The system of claim 1 , wherein the transcript is generated from audio data using automatic speech recognition (ASR).

5 . The system of claim 1 , wherein the LLM prompt is further generated based on a count of speakers identified in the summary.

6 . The system of claim 1 , wherein the topic-specific data comprises calendar information from the CRM or enterprise suite data set.

7 . The system of claim 1 , wherein the topic-specific data comprises a CRM interaction history of one of the participants.

8 . A computer-implemented method comprising:

receiving a transcript of a conversation between participants;

generating a summary of the transcript of using a summarization model, the summary relating to a topic of the conversation;

extracting topic-specific data associated with the topic of conversation from a customer relations management (CRM) or enterprise suite data set using a scoring model, the CRM or enterprise data set excluding the transcript;

dynamically generating a large language model (LLM) prompt based on the summary by resolving a difference between the topic-specific data and the summary in favor of the topic-specific data; and

generating, by an LLM model, an output text based on the LLM prompt.

9 . The computer-implemented method of claim 8 , further comprising:

transmitting, across a computer network, the output text as an electronic mail (email) message.

10 . The computer-implemented method of claim 8 , wherein the topic of the conversation comprises an action item extracted from the transcript.

11 . The computer-implemented method of claim 8 , wherein the transcript is generated from audio data using automatic speech recognition (ASR).

12 . The computer-implemented method of claim 8 , wherein the LLM prompt is further generated based on a count of speakers identified in the summary or an interaction history associated with a name identified in the summary.

13 . The computer-implemented method of claim 8 , wherein the topic-specific data comprises calendar information from the CRM or enterprise suite data set.

14 . The computer-implemented method of claim 8 , wherein the topic-specific data comprises a CRM interaction history of one of the participants.

15 . A computer storage device having computer-executable instructions stored thereon, which, on execution by one or more processors of a system, cause the system to perform operations comprising:

receiving a transcript of a conversation between participants;

generating a summary of the transcript using a summarization model, the summary relating to a topic of the conversation;

extracting topic-specific data associated with the topic from a customer relations management (CRM) or enterprise suite data set using a scoring model, the CRM or enterprise data set excluding the transcript;

dynamically generating a large language model (LLM) prompt based on the summary by resolving a difference between the topic-specific data and the summary in favor of the topic-specific data; and

generating, via an LLM model, an output text based on the LLM prompt.

16 . The computer storage device of claim 15 , wherein the operations further comprise:

transmitting, across a computer network, the output text as an electronic mail (email) message.

17 . The computer storage device of claim 15 , wherein the topic of the conversation comprises an action item extracted from the transcript.

18 . The computer storage device of claim 15 , wherein the transcript is generated from audio data using automatic speech recognition (ASR).

19 . The computer storage device of claim 15 , wherein the LLM prompt is further generated based on a count of speakers identified in the summary or an interaction history associated with a name identified in the summary.

20 . The computer storage device of claim 15 , wherein the topic-specific data comprises a CRM interaction history of one of the participants.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 13, 2023
From: ASI, ABED EL KADER; TSVETKOV, ALEXANDER; RONEN, ROYI; KUPER, YARIN; KEREN, SHAHAR ZVI; EISENSTADT, ROY
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 063313/0405 →
Continuity (1)
Related Publication 20240346232A1 · Oct 17, 2024
References Cited (19)
US 5948057A · Berger · 1999 [cited by examiner]
US 9564122B2 · Bretter et al. · 2017 [cited by applicant]
US 11516158B1 · Luzhnica et al. · 2022 [cited by applicant]
US 20220270008A1 · Milden · 2022 [cited by examiner]
US 20220391591A1 · Ronen · 2022 [cited by examiner]
US 20230027310A1 · Muralidharan · 2023 [cited by examiner]
US 20230040095A1 · Shang · 2023 [cited by applicant]
US 20230334263A1 · Konam · 2023 [cited by examiner]
US 20240289558A1 · Muraoka · 2024 [cited by examiner]
“Codify Intelligence with Large Language Models”, Retrieved from: https://www.nvidia.com/en-in/deep-learning-ai/solutions/large-language-models/, Retrieved Date: Mar. 16, 2023, 6 Pages. [cited by applicant]
“Salesforce Announces Einstein GPT, the World's First Generative AI for CRM”, Retrieved from: https://www.salesforce.com/news/press-releases/2023/03/07/einstein-generative-ai/, Mar. 7, 2023, 11 Pages. [cited by applicant]
Bass, Dina, “Microsoft Will Use OpenAI Tech to Write Emails for Busy Salespeople”, Retrieved from: https://www.bloomberg.com/news/articles/2023-02-02/microsoft-uses-chatgpt-maker-s-ai-to-write-emails-for-busy-salespeopl… [cited by applicant]
Betz, et al., “Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2”, In Repository of arXiv:2103.13033v1, Mar. 24, 2021, 17 Pages. [cited by applicant]
Huang, et al., “API Entity and Relation Joint Extraction from Text via Dynamic Prompt-tuned Language Model”, In Repository of arXiv:2301.03987v1, Jan. 10, 2023, 20 Pages. [cited by applicant]
Pandey, Nishant, “Conversational AI with Large Language Models”, Retrieved from: https://www.netomi.com/conversational-ai-with-large-language-models, Feb. 10, 2023, 13 Pages. [cited by applicant]
Pereira, et al., “Visconde: Multi-document QA with GPT-3 and Neural Reranking”, In Repository of arXiv:2212.09656v1, Dec. 19, 2022, 11 Pages. [cited by applicant]
Swamy, et al., “Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems”, In Repository of arXiv:2301.13268v2, Feb. 10, 2023, 10 Pages. [cited by applicant]
Greyling, Cobus, “Preventing LLM Hallucination With Contextual Prompt Engineering—An Example From OpenAI”, Retrieved from the URL: https://cobusgreyling.medium.com/preventing-llm-hallucination-with-contextual-prompt-eng… [cited by applicant]
International Search Report and Written Opinion received for PCT Application No. PCT/US2024/022904, Jun. 28, 2024, 13 pages. [cited by applicant]
Cited By (2)
US 12,645,874 US 12,748,928