How a Computer System Fact-Checks AI Language Models
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.
Original patent title: “Computer implemented methods for the automated analysis or use of data, including use of a large language model”
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. Granted to Unlikely Artificial Intelligence in 2024 with 31 claims and 12 forward citations, and it is expected to expire in 2043.
Coverage
What does this patent actually cover?
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" (claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 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.
The gap
What does this patent 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 claimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more →.
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The noveltynoveltyThe requirement that an invention be different from anything publicly known before its priority date.Read more → lies in using a *separate* processing system that translates the LLM's free-form text into a highly structured, machine-readable language with defined semantic nodes, links, reasoning steps, and computation units to perform rigorous, automated fact-checking, rather than relying on the LLM itself to self-correct.
The Patent Drawing
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Where you've seen this
Real-world examples
AI assistants providing factual summaries
Content generation tools requiring high accuracy
Automated legal document review systems
Medical information systems
Why it matters
The bigger picture
Large language models sometimes generate factually incorrect information, a phenomenon often called "hallucination." This patent addresses a critical problem by providing a mechanism to automatically verify and improve the accuracy of LLM outputs. This is important for applications where factual correctness is essential, such as in scientific research, legal analysis, or news generation, helping to build trust in AI systems.
Filed
April 17, 2023
Granted
August 27, 2024
Market context
Who's building on this
Companies in this space
Companies like Google, OpenAI, Anthropic, and Microsoft are heavily invested in improving the factual accuracy and reliability of their large language models. Startups focused on AI safety and verification also work in this area, developing methods to ensure LLM outputs are truthful and unbiased. Unlikely Artificial Intelligence Ltd, the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, is actively developing technologies in this space.
Market impact
The rise of powerful large language models has created a significant demand for solutions to combat "hallucinations" and factual errors. This patent addresses a core challenge, potentially enabling more trustworthy AI applications and driving the development of specialized AI verification tools. It could lead to a new category of "AI guardrail" products essential for enterprise adoption of LLMs.
Claim 1 — Plain English
What this patent covers
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.
The clever bit
The novelty lies in using a *separate* processing system that translates the LLM's free-form text into a highly structured, machine-readable language with defined semantic nodes, links, reasoning steps, and computation units to perform rigorous, automated fact-checking, rather than relying on the LLM itself to self-correct.
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.
Patent timeline
Application submitted to the patent office
Application published, typically 18 months after filing
Patent officially issued
Patent enters public domain
PatentBrief Score
Impact Score
High impact
Citation count
22/40
Moderately cited
Claim breadth
20/20
Very broad protection
Recency
20/20
Granted within 5 years
Assignee scale
20/20
Major company or institution
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
Heuristic Value Estimate
What this patent might be worth
$184K – $590K
Midpoint $369K · 16.6 yr remaining · industry ×1.6
Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.
Claim text not yet imported for this patent
The original legal language
Original claims
31 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Heywood, R., BENN, P., REYNOLDS, D., Zhu, Z., WARREN, S., Shah, A., Tunstall-Pedoe, W., & KRNIC, L. (2024). How a Computer System Fact-Checks AI Language Models (U.S. Patent No. 12,073,180). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/12073180/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including-12073180
Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.
Embed
Add this patent to your site
Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.
<div data-patentlens-widget data-patent-number="US12073180"></div> <script src="https://patentbrief.org/embed.js" async></script>
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 4683195 · 1987
How to Make Billions of Copies of a DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.
Cetus Corp
US 8697359 · 2014
How to Edit Genes in Human Cells Using an Engineered CRISPR System
This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.
Massachusetts Institute of Technology
US 7657849 · 2010
How the iPhone's Slide-to-Unlock Gesture Works
Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.
Apple Inc
US 4733665 · 1988
How Doctors Implant a Permanent Stent Using a Balloon
This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.
Expandable Grafts Partnership
US 4965188 · 1990
How to Make Many Copies of a DNA Piece with Heat
This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.
Cetus Corp
US 4235871 · 1980
How to Encapsulate Active Materials in Lipid Bubbles Efficiently
This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.
Individual
Semantically similar
You might also find these interesting
US 11989527 · 2024 · Unlikely Artificial Intelligence
How a Computer System Checks and Improves AI Text
US 12067362 · 2024 · Unlikely Artificial Intelligence
How a Computer System Improves Large Language Model Output with Structured Data
US 12353827 · 2025 · Unlikely Artificial Intelligence
Using Non-AI Systems to Improve AI Text Generation
US 12299406 · 2025 · Casetext
How AI Checks Documents for Policy Rules and Compliance
More to explore
More in AI & Machine Learning
US 10452978 · 2019 · Google LLC
How AI Models Understand Language Using 'Attention'
US 6523026 · 2003 · Huntsman International LLC
How Computers Find Hidden Connections Between Different Fields of Knowledge
US 11615208 · 2023 · Capital One Services LLC
How Cloud Systems Automatically Create and Train AI Data Models
US 10402750 · 2019 · Facebook Inc
How Facebook Uses Deep Learning to Predict What You Might Like
New to patents?
Common Questions
Frequently Asked Questions
What does How a Computer System Fact-Checks AI Language Models cover?
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.
Who owns patent US 12073180?
Unlikely Artificial Intelligence owns this patent, granted in 2024.
When does this patent expire?
This patent is expected to expire on April 17, 2043, when the invention enters the public domain.
What is patent US 12073180 cited by?
This patent has been cited by 12 later patents that build on its ideas.
What problem does this patent solve?
Large language models sometimes generate factually incorrect information, a phenomenon often called "hallucination." This patent addresses a critical problem by providing a mechanism to automatically verify and improve the accuracy of LLM outputs. This is important for applications where factual correctness is essential, such as in scientific research, legal analysis, or news generation, helping to build trust in AI systems.
What does this patent NOT cover?
Does not cover LLMs that fact-check themselves without using a separate processing system with a structured, machine-readable language.
Same assignee
More from Unlikely Artificial Intelligence
Patent monitoring