Conceptualizations of Information Science by Large Language Models
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper reports a comparative study of the ways in which large language models understand and represent the domain of information science. Five large language models were selected for this study, namely ChatGPT, Perplexity.ai, Google Gemini, Meta AI and Claude. A set of five prompts were utilized in this study for comparison. The findings suggest differences and variations in how these LLMs conceptualize and represent information science, its definitions and interdisciplinarity, theoretical models, and methods. Conceptualisations des sciences de l'information par les grands modèles de language RésuméCet article porte sur une étude comparative étayant comment les grands modèles de langage comprennent et représentent le domaine des sciences de l'information. Cinq grands modèles de langage ont été sélectionnés pour cette étude, c'est-à-dire ChatGPT, Perplexity.ai, Google Gemini, Meta AI et Claude. Un ensemble de cinq instructions ont été utilisés pour la comparaison au sein de cette étude. Les résultats suggèrent des différences et des variations par rapport à comment ces grands modèles de langage conceptualisent et représentent les sciences de l'information et ses définitions, ainsi que l'interdisciplinarité, les modèles théoriques et les méthodes. Mots-ClésGrands modèles de langage; GML; Sciences de l'information; Analyse de domaine
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.
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 | 0.002 | 0.016 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.000 | 0.003 |
| Scholarly communication | 0.001 | 0.018 |
| Open science | 0.002 | 0.001 |
| 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 it