Research software supporting the publication “Leveraging Large Language Models to Classify and Inspect Defects in Reinforced Autoclaved Aerated Concrete (RAAC)”

Liu, Lixu (2025) Research software supporting the publication “Leveraging Large Language Models to Classify and Inspect Defects in Reinforced Autoclaved Aerated Concrete (RAAC)”.

Dataset Details

Data creator(s):

Creators	Email	ORCID
Liu, Lixu	l.liu.9@bham.ac.uk	orcid.org/0009-0008-8011-496X

Research Data Type:

Software

DOI:

https://doi.org/10.25500/edata.bham.00001300

Publisher:

University of Birmingham

Funder:

Other

Keywords:

Large Language Models (LLMs); Reinforced Autoclaved Aerated Concrete (RAAC); Literature Analysis; Defect Classification; Inspection Methods; Natural Language Processing; High-Throughput Screening

Managing organisational unit:

Colleges (2008 onwards) > College of Engineering & Physical Sciences

UoB School, Department or Institute:

School of Engineering, Department of Civil Engineering

Date:

2 June 2025

Additional Details

Project/Grant:	C-DICE Industrial Secondement
Primary language:	English
Data processing and preparation activities:	Ran two parallel Claude 3 Opus prompts (“definition extraction” and “explicit mention check”) over the provided text corpus. Applied the seven-question defect-extraction prompt to the validated subset. Merged all resulting CSV files into one consolidated defect database via the aggregation script.
Depositing User:	Lixu Liu
Date Deposited:	02 Jun 2025 15:42
Last Modified:	02 Jun 2025 16:47