AI2: a novel explainable machine learning framework using an NLP interface
Bibliographic record
Abstract
This paper proposes a novel machine learning framework that encapsulates recent concerns of the data scientists community: accessibility and explainability. This framework, called AI2, proposes a natural language interface, making the framework accessible even to a non-expert. Traditionally, machine learning frameworks are accessible using a programming language. Python is one of the most common programming language for coding different machine learning methods. The AI2 framework, although made with Python scripts, is made to be accessed in a natural language, namely, English. Hence, the first contribution is about accessibility, allowing a non-data scientist to exploit a machine learning framework without knowing how to code. For decades, the data scientists community has known that one of the drawbacks in the machine learning field is the black-box problem. Data scientists have to create different methods to explain their results. The second contribution of this paper is to encapsulate the principle of explainability in the framework, systematically proposing not only the results but also the explanations of the results for every included machine learning algorithm.
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 | 0.007 | 0.017 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.005 | 0.008 |
| Open science | 0.005 | 0.006 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.016 | 0.004 |
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".