{
  "patent_number": "US 12353827",
  "country": "US",
  "title": "Using Non-AI Systems to Improve AI Text Generation",
  "original_title": "Computer implemented methods for the automated analysis or use of data, including use of a large language model",
  "summary": "This patent describes a method where a traditional, rule-based computer system helps a Large Language Model (LLM) generate more accurate and reliable text by providing it with better context and fact-checking.",
  "what_it_does": "This patent outlines a system where a non-LLM data processing system, which uses symbolic representations (like rules and facts), works alongside a Large Language Model (LLM). The non-LLM system takes an initial input, enhances it by accessing external knowledge sources, and then feeds this improved information to the LLM as a prompt. The LLM then uses this enhanced prompt to generate text that is more factually accurate, internally consistent, and aligned with real-world understanding. For example, if you ask an LLM about a historical event, the non-LLM system could first pull verified dates and facts from a database and provide them to the LLM, ensuring the LLM's response is grounded in reality.",
  "what_it_does_not_cover": [
    "Methods where the LLM directly accesses external knowledge sources without an intermediary non-LLM system.",
    "Systems that rely solely on statistical methods for data processing, without symbolic representations.",
    "LLM outputs that are not fact-checked or verified for accuracy.",
    "Methods where the non-LLM system does not enhance or augment the input before providing it to the LLM.",
    "LLM-based systems that operate without any external data processing system."
  ],
  "filed": "2024-10-23",
  "granted": "2025-07-08",
  "expires": "2044-10-23",
  "status": "active",
  "holder": "Unlikely Artificial Intelligence",
  "holder_url": "https://patentbrief.org/company/unlikely-artificial-intelligence",
  "inventors": [
    {
      "name": "Robert Heywood",
      "url": "https://patentbrief.org/inventor/robert-heywood"
    },
    {
      "name": "Paul BENN",
      "url": "https://patentbrief.org/inventor/paul-benn"
    },
    {
      "name": "Duncan REYNOLDS",
      "url": "https://patentbrief.org/inventor/duncan-reynolds"
    },
    {
      "name": "Ziyi Zhu",
      "url": "https://patentbrief.org/inventor/ziyi-zhu"
    },
    {
      "name": "Seth WARREN",
      "url": "https://patentbrief.org/inventor/seth-warren"
    },
    {
      "name": "Ayush Shah",
      "url": "https://patentbrief.org/inventor/ayush-shah"
    },
    {
      "name": "William Tunstall-Pedoe",
      "url": "https://patentbrief.org/inventor/william-tunstall-pedoe"
    },
    {
      "name": "Luci KRNIC",
      "url": "https://patentbrief.org/inventor/luci-krnic"
    }
  ],
  "times_cited": 0,
  "tags": [
    "ai_ml",
    "software",
    "telecommunications"
  ],
  "abstract": "There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.",
  "url": "https://patentbrief.org/patent/us/12353827/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including",
  "markdown_url": "https://patentbrief.org/patent/us/12353827/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including/md",
  "google_patents_url": "https://patents.google.com/patent/US12353827",
  "relatedPatents": [
    {
      "patentNumber": "12307349",
      "countryCode": "US",
      "title": "How an AI System Answers Financial Questions Using Specialized Bots",
      "url": "https://patentbrief.org/patent/us/12307349/systems-and-methods-of-large-language-model-driven-orchestration-of-task-specifi"
    },
    {
      "patentNumber": "9361579",
      "countryCode": "US",
      "title": "How Computers Calculate Probabilities in Large Knowledge Bases",
      "url": "https://patentbrief.org/patent/us/9361579/large-scale-probabilistic-ontology-reasoning"
    },
    {
      "patentNumber": "8285656",
      "countryCode": "US",
      "title": "How a Smart System Verifies and Updates Customer Data",
      "url": "https://patentbrief.org/patent/us/8285656/cortana-virtual-assistant"
    },
    {
      "patentNumber": "10878335",
      "countryCode": "US",
      "title": "How Computers Find Similar Text Using Compact Data Structures",
      "url": "https://patentbrief.org/patent/us/10878335/bert-bidirectional-encoder-representations"
    },
    {
      "patentNumber": "6523026",
      "countryCode": "US",
      "title": "How Computers Find Hidden Connections Between Different Fields of Knowledge",
      "url": "https://patentbrief.org/patent/us/6523026/google-search-query-processing"
    }
  ]
}