Translative Research Assistant: A Retrieval-Augmented Generation Pipeline Refinement with Keyword Extraction Using Extended Scalable Betweenness Centrality
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 objective of this research is to introduce a translation tool that addresses two critical aspects: first, the translation of research from other languages into our target language; and second, the adaptation of existing knowledge from other research to align with a researcher’s specific context. To achieve this, we propose these key approaches: summarization, keyword extraction and evaluation, which assesses the relevance of materials to a researcher’s work or identifies the need for further investigation. Our solution is the Translative Research Assistant, leveraging ChatGPT as its primary tool. To enhance the accuracy of its text generation, we advocate for a knowledge retrieval approach utilizing the Retrieval-Augmented Generation pipeline with keyword extraction using proposed Extended Scalable Betweenness Centrality. Ultimately, our aim is to promote the integration of AI across disciplines and enhance the precision of ChatGPT responses, aiding researchers in efficiently assessing the utility of new information they encounter.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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