Verified Data Source Retrieval for Grounded AI Reports

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Generative AI systems often produce hallucinations due to a lack of grounding in real-world knowledge, leading to factually incorrect or nonsensical outputs.

Innovation Solution

A system that identifies verified data sources for each piece of data within a query, retrieves data from these sources, and uses generative AI to generate reports with citations to these sources, thereby reducing hallucinations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If generative AI is used to create content, then productivity is improved, but reliability deteriorates due to hallucinations

Engineering Contradiction:

Improvereport generation speedVSAvoiddata accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent introduces verified data sources as intermediaries between the user query and the generative AI model. The system identifies and retrieves data from trusted sources (databases, documents, websites) before feeding it to the generative AI, ensuring the AI has accurate information to work with rather than generating content from scratch based on potentially incorrect training data

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary actions by first parsing the user query to extract data requirements, then proactively searching for and retrieving verified data before the generative AI generates the report. This preliminary data retrieval ensures the AI receives accurate, ground truth information rather than relying on its training data alone

Inventive Principle:

Principle #10Preliminary action

2Reliability

If verified data sources are identified and queries are generated, then reliability is improved, but device complexity increases

Engineering Contradiction:

Improvedata accuracyVSAvoidsystem structure

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the report generation task into distinct functional modules: query parsing module, verified data source identification module, data retrieval module, and generative AI report generation module. This segmentation allows each component to focus on a specific function, making the overall complex system more manageable and maintainable

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system uses a multi-functional approach where the same generative AI model serves multiple purposes: it parses user queries, identifies data requirements, generates search queries for verified sources, and finally generates the report. This multi-functionality reduces the need for separate specialized components for each task

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20260064738A1System and method for identifying data sources for generative artificial intelligence

Publication Date: 2026.03.05 TRUE ELEMENTS INC

AI summary

Systems, methods, and computer-readable storage media for identifying databases or resources which contain verifiable information used to create generative AI output. A system can receive a request for generation of a report, the request including a string of text. The system can then parse the string, resulting in a parsed request, and identify at least one verified data source for each piece of data within the parsed request. The system can then generate a query for each verified data source based on the parsed request, resulting in at least one query, and send those queries to the verified data sources. Those sources can respond with verified data, and the system can generate, using a generative Artificial Intelligence (AI) algorithm, the report using the verified data.