Can this robot query my Linked Data Store? Exploring retrieval-augmented models for Repository Search & Discovery
Bibliographic record
Abstract
The University of Toronto Scarborough Library's Digital Scholarship Unit has been developing multiformat and multilingual digital collections for over ten years, with a focus on post-custodial and non-extractive models. This presentation explores the integration of linked data and AI-powered chat-based search, using one specific project as a use case. The Dragomans project, which explores the role of diplomatic interpreter-translators in the Ottoman Empire, provides a multilingual dataset with linked data that allows us to assess the effectiveness of various retrieval-augmented generation methods when implementing chat-based search. This research offers insights that are applicable across various knowledge domains. The limitations of generative artificial intelligence in handling structured data, complex reasoning, and contextual understanding are well described. We compare various retrieval-augmented models to direct SPARQL/CIPHER queries and compare the results. This allows us to evaluate these approaches and comment on their effectiveness as well as resource implications. Our findings uniquely illuminate the landscape of generative AI, providing valuable guidance for future repository infrastructure development and contributing to the broader discourse on the integration of AI and linked data in digital repositories.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.006 | 0.010 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".