DOL · DOL-45 · record R1311

NLP Processing tool for ILAB

Department of Labor · CEO-ILAB

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: Only query and returining answers
Start date: Not reported
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Service Delivery
Operational functions: Chatbot or virtual assistant, Summarization, Search and knowledge retrieval Derived by keyword rules; see methodology

Problem the AI is intended to solve

The Natural Language Processing tool is intended to be a conversational query and synthesis tool that summarizes and synthesizes evaluation and technical assistance reports, as well as responses to requests for public comments, and queries information contained in these reports. The tool uses a Retrieval-Augmented Generation (RAG) approach and will include processing of both publicly available and restricted-access documents to train and test the tool.

Expected benefits

Rapidly summarizes and synthesizes large volumes of evaluation and technical assistance reports, thereby increasing efficiency

System outputs

The tool responds to queries by providing information summarized from reports and other documents.

Technology

AI classification: Generative AISource: Generative AI: AI that generates new or synthetic content (e.g., images, videos, audio, text, code).
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