eprintid: 2536
rev_number: 12
eprint_status: archive
userid: 192
dir: disk0/00/00/25/36
datestamp: 2024-11-13 00:00:51
lastmod: 2024-11-13 00:00:51
status_changed: 2024-11-13 00:00:51
type: conference_item
metadata_visibility: show
creators_name: Kimbrough, John
title: MARC Records with ChatGPT: Lessons Learned
ispublished: pub
subjects: alma
subjects: gen
abstract: Georgetown University undertook a small pilot project this summer to test ChatGPT’s ability to produce MARC records for items in various formats. I would like to share some lessons we learned, including what the AI got right, frequent errors made by ChatGPT, and workflows for proofreading records as a team. The lessons have helped inform us about using the Alma AI Metadata Assistant, and to evaluate its output.
date: 2024-10-25
full_text_status: public
pres_type: lecture
event_title: DCRUG Annual Meeting 2024
event_type: conference
refereed: FALSE
citation: Kimbrough, John (2024) MARC Records with ChatGPT: Lessons Learned. In: DCRUG Annual Meeting 2024.
document_url: https://beta-documents.el-una.org/id/eprint/2536/1/DCRUG-MARC%20Records%20with%20ChatGPT-2024%20Annual.pdf