A Question-Answering System on COVID-19 Scientific Literature
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
The vast amount of COVID-19 research literature has made it difficult for medical experts, clinical scientists, and researchers to keep up with the latest research findings. We present two datasets for COVID-19 in this work: (1) first, we create a dataset from the up-to-date scientific publications on COVID-19, and (2) second, we build a gold-standard dataset of question-answering pairs annotated by volunteer biomedical experts on COVID-19 related scientific articles. We develop a question-answering (QA) pipeline that uses the first dataset to provide answers related to COVID-19 questions; we fine-tune MPNet (a Transformer model) on our gold-standard dataset and use it in the QA pipeline to enhance its reading capability. We also use this gold-standard dataset to evaluate the QA pipeline. The proposed MPNet version on the gold-standard dataset outperformed previous datasets and models, achieving an Exact Match/Fl score of 69.72/78.50 %, respectively
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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