Research on Multi-Label Legal Text Categorization Methods Based on Large Predicate Models
Bibliographic record
Abstract
In this paper, the embedding vectors are obtained by Bert coding, and then the obtained embedding vectors are adaptively fused with features to realize legal text classification by a classifier, on the basis of which a multi-label text classification model (AFDAM) is proposed to capture the target words in a sentence. At the same time, the pre-trained continuous bag-of-words representation (CBOW) is used to initialize the vector representation of the label information, and then these label information is adaptively fused with the feature information of the text, which effectively promotes the multi-label legal text classification, and accelerates the development of informationization and intelligence in the legal field. The results show that the text feature enhancement module has the most prominent impact on the text classification effect, and its accuracy on the three datasets is improved by 0.46%-1.19%. In addition, the introduction of target vectors and text expansion also gained 0.54%-1.7% and 0.59%-1.53% and 1.08% increases in model accuracy, respectively. In addition, the addition of offense and statute information can significantly improve the prediction of sentence length, and the statute information improves the results more significantly than the offense information. And the classification effect of the AFDAM model proposed in this paper increased by 0.1453-0.257 than the other five models.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.008 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".