The Training Process and Methods for LLMs Using an Own Knowledge Base
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 explores the development of frameworks and training methods for large language models (LLMs), focusing on the importance of self-built data (Own data or Own Knowledge Base), specific processes of model pre-training and fine-tuning, and model performance evaluation and deployment effects. By introducing and analysing the advantages and disadvantages of mainstream large language models (such as GPT-4, BERT, LLaMA, and Mistral), we illustrate the strengths and limitations of large language models in natural language processing tasks. This paper particularly emphasises the critical role of self-built data in enhancing the model's professionalism and accuracy, discussing data collection and processing methods. We detail the steps of model pre-training and their impact on model performance, explore the necessity and implementation of model fine-tuning, and validate the effectiveness of the proposed framework training method through performance evaluation metrics and actual deployment effects.
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 | 0.005 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.001 | 0.000 |
| 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