Towards Standards-Compliant Assistive Technology Product Specifications via LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912183707762688 |
|---|---|
| author | Arora, Chetan Grundy, John Puli, Louise Layton, Natasha |
| author_facet | Arora, Chetan Grundy, John Puli, Louise Layton, Natasha |
| contents | In the rapidly evolving field of assistive technology (AT), ensuring that products meet national and international standards is essential for user safety, efficacy, and accessibility. In this vision paper, we introduce CompliAT, a pioneering framework designed to streamline the compliance process of AT product specifications with these standards through the innovative use of Large Language Models (LLMs). CompliAT addresses three critical tasks: checking terminology consistency, classifying products according to standards, and tracing key product specifications to standard requirements. We tackle the challenge of terminology consistency to ensure that the language used in product specifications aligns with relevant standards, reducing misunderstandings and non-compliance risks. We propose a novel approach for product classification, leveraging a retrieval-augmented generation model to accurately categorize AT products aligning to international standards, despite the sparse availability of training data. Finally, CompliAT implements a traceability and compliance mechanism from key product specifications to standard requirements, ensuring all aspects of an AT product are thoroughly vetted against the corresponding standards. By semi-automating these processes, CompliAT aims to significantly reduce the time and effort required for AT product standards compliance and uphold quality and safety standards. We outline our planned implementation and evaluation plan for CompliAT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03122 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Standards-Compliant Assistive Technology Product Specifications via LLMs Arora, Chetan Grundy, John Puli, Louise Layton, Natasha Software Engineering In the rapidly evolving field of assistive technology (AT), ensuring that products meet national and international standards is essential for user safety, efficacy, and accessibility. In this vision paper, we introduce CompliAT, a pioneering framework designed to streamline the compliance process of AT product specifications with these standards through the innovative use of Large Language Models (LLMs). CompliAT addresses three critical tasks: checking terminology consistency, classifying products according to standards, and tracing key product specifications to standard requirements. We tackle the challenge of terminology consistency to ensure that the language used in product specifications aligns with relevant standards, reducing misunderstandings and non-compliance risks. We propose a novel approach for product classification, leveraging a retrieval-augmented generation model to accurately categorize AT products aligning to international standards, despite the sparse availability of training data. Finally, CompliAT implements a traceability and compliance mechanism from key product specifications to standard requirements, ensuring all aspects of an AT product are thoroughly vetted against the corresponding standards. By semi-automating these processes, CompliAT aims to significantly reduce the time and effort required for AT product standards compliance and uphold quality and safety standards. We outline our planned implementation and evaluation plan for CompliAT. |
| title | Towards Standards-Compliant Assistive Technology Product Specifications via LLMs |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2404.03122 |