# How to Check if a Large Language Model's Answer is True > Amazon's patent details a system for verifying large language model responses by having a second AI translate the answer into formal logic, which an automated theorem prover then checks for validity or invalidity. - **Patent:** US 20250200392 - **Original title:** Large language model verification - **Owner:** Amazon Technologies - **Status:** Active - **Times cited:** 12 - **Field:** ai_ml, software, telecommunications, consumer_electronics ## What it does This patent describes a method for verifying answers from a large language model (LLM). First, a system obtains a 'conversational text' which includes a user's question (query) and the answer from a first LLM. Then, a *second* large language model translates this answer into 'first-order logic,' which is a formal way to represent statements and relationships (Claim 1). An automated theorem prover, specifically a 'satisfiability modulo theories solver,' then checks this logic translation. It determines if the answer is 'valid' by checking if its negation is impossible (unsatisfiable), and if it's 'invalid' by checking if the answer itself is impossible (Claim 1). Finally, the system outputs whether the answer is valid, invalid, or neither, to a user interface, database, or report. ## What it does NOT cover - Does not cover verifying LLM answers without translating them into first-order logic. - Does not cover verification methods that do not use an automated theorem prover or satisfiability modulo theories solver. - Does not cover systems where the first LLM directly provides the first-order logic translation without a second LLM. - Does not cover verifying answers that are not derived from a query-response conversational text from an LLM. - Does not cover systems that only determine validity or invalidity without also identifying 'neither valid nor invalid'. ## The clever bit The novelty lies in using a *second* large language model to translate a natural language answer into a formal 'first-order logic' representation. This allows a traditional, rigorous automated theorem prover to then formally check the truthfulness of the answer, bridging the gap between flexible AI output and strict logical verification. ## Real-world examples 1. AI assistants providing factual summaries of documents 2. Generative AI tools for legal research 3. Medical diagnostic support systems using LLMs 4. Automated code generation and verification 5. Customer service chatbots providing policy information ## Why it matters Large language models sometimes generate incorrect or misleading information, a problem often called 'hallucination.' This patent offers a structured, automated way to check the factual accuracy of LLM outputs. By providing a formal verification process, it aims to make LLMs more reliable for critical applications where accuracy is paramount, such as in scientific research, legal analysis, or financial advice. ## Frequently asked questions ### What does How to Check if a Large Language Model's Answer is True cover? Amazon's patent details a system for verifying large language model responses by having a second AI translate the answer into formal logic, which an automated theorem prover then checks for validity or invalidity. ### Who owns patent US 20250200392? This patent is owned by Amazon Technologies. ### When does this patent expire? This patent is expected to expire on December 15, 2043, when the invention enters the public domain. ### What is patent US 20250200392 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 incorrect or misleading information, a problem often called 'hallucination.' This patent offers a structured, automated way to check the factual accuracy of LLM outputs. By providing a formal verification process, it aims to make LLMs more reliable for critical applications where accuracy is paramount, such as in scientific research, legal analysis, or financial advice. ### What does this patent NOT cover? Does not cover verifying LLM answers without translating them into first-order logic. **Full plain-English explainer:** https://patentbrief.org/patent/us/20250200392/large-language-model-verification **Original patent:** https://patents.google.com/patent/US20250200392 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How a Computer System Checks and Improves AI Text](https://patentbrief.org/patent/us/11989527/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including-11989527) — This patent describes a method where a separate computer system, using structured knowledge, checks and corrects the output from a large language model to make it more accurate and consistent. - [How a Computer System Fact-Checks AI Language Models](https://patentbrief.org/patent/us/12073180/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including-12073180) — 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. - [How Chatbots Use AI and Fact Databases to Learn and Improve](https://patentbrief.org/patent/us/12531820/knowledge-graph-assisted-large-language-models) — This patent describes how a chatbot can combine the broad answering abilities of a large language model with a structured knowledge graph to provide more accurate, verifiable, and debuggable responses, especially for repeat questions. - [How a Computer System Improves Large Language Model Output with Structured Data](https://patentbrief.org/patent/us/12067362/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including-12067362) — This patent describes a method where a separate computer system analyzes and refines the initial output from a large language model (LLM) by translating it into a highly structured, machine-readable language to reduce bias and improve accuracy. - [Using Non-AI Systems to Improve AI Text Generation](https://patentbrief.org/patent/us/12353827/computer-implemented-methods-for-the-automated-analysis-or-use-of-data-including) — 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.