The AI-powered archivist: Harnessing generative artificial intelligence for streamlined archival description
Bibliographic record
Abstract
This paper describes the Generative AI and Description Project started by the University of Alberta Archives team in January 2024. Stemming from a curiosity to explore the ways in which generative artificial intelligence (GenAI) can be incorporated into daily workflows, the project sought to find ways of streamlining and saving time on some of the more laborious tasks of archival description. The team focused the implementation of GenAI tools on the creation of biographical sketches and administrative histories. Three GenAI tools were chosen, based on their open access and familiarity to most — ChatGPT, Perplexity AI and Microsoft’s CoPilot. Person and organisation-based entities were selected for the trials. As the project progressed, detailed processing notes were taken to track the accuracy of each tool used in the development of an appropriate and useful biographical sketch or administrative history. The results indicated a varying degree of inconsistency and fabrication (ie errors or inaccurate information) across the three tools, highlighting the need for staff to proofread and confirm the validity of sources; thus, not saving significant time in the end. The goal of this project was to provide other archives professionals with specific examples of practical applications of GenAI tools in archival description workflows. We hope that this project can inspire others to explore other ways in which GenAI can become a part of our professional practices. This article is also included in The Business & Management Collection, which can be accessed at https://hstalks.com/business/.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".