Large language models for closed-library multi-document query, test generation, and evaluation

IntroductionLearning complex, detailed, and evolving knowledge is a challenge in multiple technical professions. Relevant source knowledge is contained within many large documents and information sources with frequent updates to these documents. Knowledge tests need to be generated on new material a...

Full description

Saved in:
Bibliographic Details
Main Authors: Claire Randolph, Adam Michaleas, Darrell O. Ricke
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1592013/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849236496472604672
author Claire Randolph
Adam Michaleas
Darrell O. Ricke
author_facet Claire Randolph
Adam Michaleas
Darrell O. Ricke
author_sort Claire Randolph
collection DOAJ
description IntroductionLearning complex, detailed, and evolving knowledge is a challenge in multiple technical professions. Relevant source knowledge is contained within many large documents and information sources with frequent updates to these documents. Knowledge tests need to be generated on new material and existing tests revised, tracking knowledge base updates. Large Language Models (LLMs) provide a framework for artificial intelligence-assisted knowledge acquisition and continued learning. Retrieval-Augmented Generation (RAG) provides a framework to leverage available, trained LLMs combined with technical area-specific knowledge bases.MethodsHerein, two methods are introduced (DaaDy: document as a dictionary and SQAD: structured question answer dictionary), which together enable effective implementation of LLM-RAG question-answering on large documents. Additionally, the AI for knowledge intensive tasks (AIKIT) solution is presented for working with numerous documents for training and continuing education. AIKIT is provided as a containerized open source solution that deploys on standalone, high performance, and cloud systems. AIKIT includes LLM, RAG, vector stores, relational database, and a Ruby on Rails web interface.ResultsCoverage of source documents by LLM-RAG generated questions decreases as the length of documents increase. Segmenting source documents improve coverage of generated questions. The AIKIT solution enabled easy use of multiple LLM models with multimodal RAG source documents; AIKIT retains LLM-RAG responses for queries against one or multiple LLM models.DiscussionAIKIT provides an easy-to-use set of tools to enable users to work with complex information using LLM-RAG capabilities. AIKIT enables easy use of multiple LLM models with retention of LLM-RAG responses.
format Article
id doaj-art-083d155f8f474989aceb2a660096ba2b
institution Kabale University
issn 2624-8212
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-083d155f8f474989aceb2a660096ba2b2025-08-20T04:02:13ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-08-01810.3389/frai.2025.15920131592013Large language models for closed-library multi-document query, test generation, and evaluationClaire Randolph0Adam Michaleas1Darrell O. Ricke2Department of the Air Force, Artificial Intelligence Accelerator, Cambridge, MA, United StatesAI Technology, MIT Lincoln Laboratory, Lexington, MA, United StatesAI Technology, MIT Lincoln Laboratory, Lexington, MA, United StatesIntroductionLearning complex, detailed, and evolving knowledge is a challenge in multiple technical professions. Relevant source knowledge is contained within many large documents and information sources with frequent updates to these documents. Knowledge tests need to be generated on new material and existing tests revised, tracking knowledge base updates. Large Language Models (LLMs) provide a framework for artificial intelligence-assisted knowledge acquisition and continued learning. Retrieval-Augmented Generation (RAG) provides a framework to leverage available, trained LLMs combined with technical area-specific knowledge bases.MethodsHerein, two methods are introduced (DaaDy: document as a dictionary and SQAD: structured question answer dictionary), which together enable effective implementation of LLM-RAG question-answering on large documents. Additionally, the AI for knowledge intensive tasks (AIKIT) solution is presented for working with numerous documents for training and continuing education. AIKIT is provided as a containerized open source solution that deploys on standalone, high performance, and cloud systems. AIKIT includes LLM, RAG, vector stores, relational database, and a Ruby on Rails web interface.ResultsCoverage of source documents by LLM-RAG generated questions decreases as the length of documents increase. Segmenting source documents improve coverage of generated questions. The AIKIT solution enabled easy use of multiple LLM models with multimodal RAG source documents; AIKIT retains LLM-RAG responses for queries against one or multiple LLM models.DiscussionAIKIT provides an easy-to-use set of tools to enable users to work with complex information using LLM-RAG capabilities. AIKIT enables easy use of multiple LLM models with retention of LLM-RAG responses.https://www.frontiersin.org/articles/10.3389/frai.2025.1592013/fulllarge language modelsLLMretrieval-augmented generationRAGLangChain
spellingShingle Claire Randolph
Adam Michaleas
Darrell O. Ricke
Large language models for closed-library multi-document query, test generation, and evaluation
Frontiers in Artificial Intelligence
large language models
LLM
retrieval-augmented generation
RAG
LangChain
title Large language models for closed-library multi-document query, test generation, and evaluation
title_full Large language models for closed-library multi-document query, test generation, and evaluation
title_fullStr Large language models for closed-library multi-document query, test generation, and evaluation
title_full_unstemmed Large language models for closed-library multi-document query, test generation, and evaluation
title_short Large language models for closed-library multi-document query, test generation, and evaluation
title_sort large language models for closed library multi document query test generation and evaluation
topic large language models
LLM
retrieval-augmented generation
RAG
LangChain
url https://www.frontiersin.org/articles/10.3389/frai.2025.1592013/full
work_keys_str_mv AT clairerandolph largelanguagemodelsforclosedlibrarymultidocumentquerytestgenerationandevaluation
AT adammichaleas largelanguagemodelsforclosedlibrarymultidocumentquerytestgenerationandevaluation
AT darrelloricke largelanguagemodelsforclosedlibrarymultidocumentquerytestgenerationandevaluation