Enriching Human–AI Collaboration: The Ontological Service Framework Leveraging Large Language Models for Value Creation in Conversational AI
Bibliographic record
Abstract
This research focuses on ontology-driven conversational agents (CAs) that harness large language models (LLMs) and their mediating role in performing collective tasks and facilitating knowledge-sharing capabilities among multiple healthcare stakeholders. The research addresses how CAs can promote a therapeutic working alliance and foster trustful human–AI collaboration between emergency department (ED) stakeholders, thereby supporting collaborative tasks with healthcare professionals (HPs). The research contributes to developing a service-oriented human–AI collaborative framework (SHAICF) to promote co-creation and collaborative learning among patients, CAs, and HPs, and improve information flow procedures within the ED. The research incorporates agile heavy-weight ontology engineering methodology (OEM) rooted in the design science research method (DSRM) to construct an ontological metadata model (PEDology), which underpins the development of semantic artifacts. A customized OEM is used to address the issues mentioned earlier. The shared ontological model framework helps developers to build AI-based information systems (ISs) integrated with LLMs’ capabilities to comprehend, interpret, and respond to complex healthcare queries by leveraging the structured knowledge embedded within ontologies such as PEDology. As a result, LLMs facilitate on-demand health-related services regarding patients and HPs and assist in improving information provision, quality care, and patient workflows within the ED.
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 | 0.010 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.003 | 0.009 |
| Scholarly communication | 0.008 | 0.015 |
| Open science | 0.003 | 0.010 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.002 | 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".