FDIC · FDIC – 53 · record R1075

Trust Document Entity Extraction - LLM

Federal Deposit Insurance Corporation · Division of Resolutions and Receiverships

Overview

Development stage: In development or acquisitionSource: a) Pre-deployment – The use case is in a development or acquisition status.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: Not reported
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Other
Operational functions: Document processing and extraction Derived by keyword rules; see methodology

Problem the AI is intended to solve

The current trust document review process is labor intensive and may require further reviews by legal experts, hence, prolonging the processing time. By leveraging the use of a Large Language Model to automate the extraction of key information from trust agreements to match and verify customer form input, this will lead to a faster, accurate and efficient workflow for claims specialists.

Expected benefits

The current trust document review process is labor intensive and may require further reviews by legal experts, hence, prolonging the processing time. Using a LLM to automate the extraction of data will reduce manual effort and improve the quality of data extracted from trust documents.

System outputs

By using the LLM, the extracted data will include key data elements, such as grantor/settler and beneficiaries from Trust Agreements along with the original Trust Agreement, which will be presented to users through an application user interface. This will automate the extraction of key information from trust agreements to match and verify customer form inputs.

Technology

AI classification: Natural language processingSource: Natural Language Processing: AI that processes, interprets, and shares information in human language.
System name(s): Not reported
Custom-developed code: Not reported
Public source code: Not reported

Sourcing

How it was built: Not reported
Vendor (as reported): Not reported
Vendors (standardized): None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: Not reported
Privacy Impact Assessment: Not reported
Authorization to Operate: Not reported
Demographic features: Not reported
Training and evaluation data: Not reported
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported