Towards a LLM-Based System for Generating and Validating Product Requirements

This position paper motivates the development of a large language model (LLM) -based system for creating comprehensive, testable product requirements documents (PRDs). The intention is to guide innovators who lack formal product management experience— clinicians, researchers, academics, and other specialists—in producing specifications detailed enough for successful contracting with engineering or manufacturing partners. The LLM would be augmented with a retrieval-augmented generation (RAG) component and set up in a conversational manner, mitigating issues that arise when under-specified requirements are handed to contract firms.

Authors

Institutions

Publication Details

Published
2025-06-23
DOI
https://doi.org/10.1145/3696630.3731673
Citations
1
Primary Topic
Software Engineering Techniques and Practices
Type
article
Field-Weighted Citation Impact
3.25

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Towards a LLM-Based System for Generating and Validating Product Requirements

T. A. Carpenter, Kevin Leach, James E. Weimer, E. R. Krueger
1 citations
Software Engineering Techniques and Practices
3.25
article

Towards a LLM-Based System for Generating and Validating Product Requirements

T. A. Carpenter, Kevin Leach, James E. Weimer, E. R. Krueger
article en
1 citations

Abstract

This position paper motivates the development of a large language model (LLM) -based system for creating comprehensive, testable product requirements documents (PRDs). The intention is to guide innovators who lack formal product management experience— clinicians, researchers, academics, and other specialists—in producing specifications detailed enough for successful contracting with engineering or manufacturing partners. The LLM would be augmented with a retrieval-augmented generation (RAG) component and set up in a conversational manner, mitigating issues that arise when under-specified requirements are handed to contract firms.

Vanderbilt University (US)
National Science Foundation
Openalex Percentile: Top 7%
Software Engineering Techniques and Practices
3.25
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.