{
  "patent_number": "US 12073180",
  "country": "US",
  "title": "How a Computer System Fact-Checks AI Language Models",
  "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 for a separate computer system to fact-check and improve the output of a large language model by translating its text into a structured, machine-readable format.",
  "what_it_does": "The patent describes a computer-implemented method for fact-checking the output of a large language model (LLM). First, the LLM processes an initial prompt to generate text, referred to as \"first output\" (claim 1a). This \"first output\" is then provided to a separate \"processing system\" (claim 1c). This processing system uses a special \"structured, machine-readable representation of data\" that conforms to a \"machine-readable language\" (claim 1b). This language represents specific meanings as \"semantic nodes\" and includes \"semantic links\" between them, along with \"reasoning steps\" and \"computation units\" (claim 1b). The processing system translates factual assertions from the LLM's output into this structured language (claim 2) and then analyzes it for factual inaccuracies (claim 3), contradictions (claim 4), and even bias (claim 13). Using its built-in reasoning steps and computation units, it generates a \"second output,\" which is a fact-checked and improved version of the original text, and provides it to the user (claim 1d). For example, if an LLM incorrectly states \"The capital of France is Berlin,\" the processing system would translate this assertion, check it against its structured knowledge, identify the inaccuracy, and then provide the corrected information \"The capital of France is Paris\" to the user.",
  "what_it_does_not_cover": [
    "Does not cover LLMs that fact-check themselves without using a separate processing system with a structured, machine-readable language.",
    "Does not cover fact-checking methods that do not translate the LLM's output into a specific structured, machine-readable representation with semantic nodes and links.",
    "Does not cover systems where the fact-checking process does not involve \"reasoning steps\" and \"computation units\" represented in the machine-readable language.",
    "Does not cover simply comparing LLM output to a database without the semantic analysis described in the claims."
  ],
  "filed": "2023-04-17",
  "granted": "2024-08-27",
  "expires": "2043-04-17",
  "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": 12,
  "tags": [
    "ai_ml",
    "software",
    "telecommunications",
    "consumer_electronics"
  ],
  "abstract": "Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.",
  "url": "https://patentbrief.org/patent/us/12073180/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including-12073180",
  "markdown_url": "https://patentbrief.org/patent/us/12073180/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including-12073180/md",
  "google_patents_url": "https://patents.google.com/patent/US12073180",
  "relatedPatents": [
    {
      "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"
    },
    {
      "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": "12299406",
      "countryCode": "US",
      "title": "How AI Checks Documents for Policy Rules and Compliance",
      "url": "https://patentbrief.org/patent/us/12299406/large-language-model-artificial-intelligence-text-evaluation-system"
    },
    {
      "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"
    }
  ]
}