{
  "patent_number": "US 20250094707",
  "country": "US",
  "title": "How to Make AI Smarter by Secretly Adding Facts to Your Questions",
  "original_title": "Supplementation of large language model knowledge via prompt modification",
  "summary": "This patent describes a system that automatically finds important words in your questions to an AI, then adds relevant facts from a knowledge base before the AI answers, making the AI's response more informed without you knowing the extra facts were added.",
  "what_it_does": "This system improves how large language models (LLMs) respond by automatically adding extra information to a user's question. First, it receives user input, like a question or statement (Claim 1). It then analyzes this input to find key 'entities' — specific people, places, or things mentioned (Claim 1). Using a 'semantic framework,' which is like a structured database of facts (Claim 4, e.g., a knowledge graph), it looks up information related to these entities. This information is often in the form of 'triples' (subject, predicate, object, like 'Apple Inc. designs iPhones') (Claim 1). These triples can be turned into plain sentences, called 'verbalized triples' (Claim 3). The system then adds these extra facts to the original user input, creating a 'modified user input' (Claim 1). This modified input is sent to the LLM, which uses the added facts to generate a more complete response. Crucially, the user only sees the original question and the LLM's final answer; the added facts are hidden (Claim 9). For example, if a user asks, 'Tell me about the CEO of Apple,' the system might secretly add facts like 'Tim Cook is the CEO of Apple Inc.' and 'Apple Inc. is a technology company' to the prompt before the LLM processes it.",
  "what_it_does_not_cover": [
    "Does not cover systems where the user explicitly provides all the supplemental information to the large language model.",
    "Does not cover systems that only use a large language model without an external semantic framework or knowledge graph to find additional facts.",
    "Does not cover methods where the modified user input, including the added facts, is displayed to the user before being sent to the LLM.",
    "Does not cover systems that only identify entities in the user input without then using those entities to retrieve and add 'triples' or similar structured data.",
    "Does not cover general prompt engineering techniques that manually add context or instructions to an LLM prompt."
  ],
  "filed": "2023-09-15",
  "granted": null,
  "expires": "2043-09-15",
  "status": "active",
  "holder": "SAP SE",
  "holder_url": "https://patentbrief.org/company/sap-se",
  "inventors": [
    {
      "name": "Jan Portisch",
      "url": "https://patentbrief.org/inventor/jan-portisch"
    },
    {
      "name": "Yannis Reitemeier",
      "url": "https://patentbrief.org/inventor/yannis-reitemeier"
    },
    {
      "name": "Michael Hladik",
      "url": "https://patentbrief.org/inventor/michael-hladik"
    },
    {
      "name": "Guilherme COSTA",
      "url": "https://patentbrief.org/inventor/guilherme-costa"
    },
    {
      "name": "Deepak Sahu",
      "url": "https://patentbrief.org/inventor/deepak-sahu"
    }
  ],
  "times_cited": 12,
  "tags": [
    "software",
    "ai_ml",
    "telecommunications",
    "enterprise_software",
    "data_management"
  ],
  "abstract": "The present disclosure provides techniques and solutions for automatically and dynamically supplementing user prompts to large language models with information to be used by the large language model in formulating a response. In particular, entities are identified in the original prompt. A semantic framework is searched for information about such entities, and such information is added to the original user prompt to provide a modified user prompt. In a particular example, the identified entities comprise triples, and verbalized triples are added to provide the modified user prompt. The modified prompt may be hidden from the user, so that a response of the large language model appears to be in response to the original prompt.",
  "url": "https://patentbrief.org/patent/us/20250094707/supplementation-of-large-language-model-knowledge-via-prompt-modification",
  "markdown_url": "https://patentbrief.org/patent/us/20250094707/supplementation-of-large-language-model-knowledge-via-prompt-modification/md",
  "google_patents_url": "https://patents.google.com/patent/US20250094707",
  "relatedPatents": [
    {
      "patentNumber": "12531820",
      "countryCode": "US",
      "title": "How Chatbots Use AI and Fact Databases to Learn and Improve",
      "url": "https://patentbrief.org/patent/us/12531820/knowledge-graph-assisted-large-language-models"
    },
    {
      "patentNumber": "12353827",
      "countryCode": "US",
      "title": "Using Non-AI Systems to Improve AI Text Generation",
      "url": "https://patentbrief.org/patent/us/12353827/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including"
    },
    {
      "patentNumber": "12073180",
      "countryCode": "US",
      "title": "How a Computer System Fact-Checks AI Language Models",
      "url": "https://patentbrief.org/patent/us/12073180/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including-12073180"
    },
    {
      "patentNumber": "11989527",
      "countryCode": "US",
      "title": "How a Computer System Checks and Improves AI Text",
      "url": "https://patentbrief.org/patent/us/11989527/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including-11989527"
    },
    {
      "patentNumber": "12067362",
      "countryCode": "US",
      "title": "How a Computer System Improves Large Language Model Output with Structured Data",
      "url": "https://patentbrief.org/patent/us/12067362/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including-12067362"
    }
  ]
}