Finding connections between fundamentally different conceptions of "models"
Bibliographic record
Abstract
One of the major projects in the DH has been to find meanings in text through digital means—text analysis—and the recent the emergence of Large Language Models has presented a radically new extension to this. In contrast, almost all my professional DH life at KCL (in 25 substantial funded DH projects) has centered not on text analysis but representation through highly structured data (usually in terms of the relational database). Also, my Pliny project has explored how aspects of the more informal process of humanities research which is, at least in good part, about finding new interpretations could be usefully supported digitally. Both Pliny and most of the highly structured projects have text "nestled" within them. Both highly structured data and LLMs create models expressing some the semantics of their material, but LLM's models are very different kind of thing from models represented by graph-oriented highly structured data projects (and in Pliny). Is there any point of connection? To explore this issue we have built mechanisms to extract the textual bits from Record of Early English Drama's (U of Toronto) EMLoT resource, and from the Pliny dataset of a significant Pliny user. Text analysis techniques have then been applied to uncover structure. We have begun this work with Voyant, and continued by applying basic LLM models and examined how these language Models might characterize these texts. Text operating semantically can be found in highly structured data, and particularly in Pliny. Hence, part of the semantic significance of these projects is not found only in their object structure, but also in the text in these structures, and the semantic meaning between the text and the data structure is likely to be complementary. This poster reveals some initial ways in which points of contact can be found in these data structure and text visualizations. Do they enable a fuller vision of what our materials represent than either do by themselves?
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 | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".