Research on legal judgment prediction model based on event extraction and constraints
Bibliographic record
Abstract
Research on event extraction and constraint encoding of legal cases, using Lawformer as a pre-trained language model for legal sentence prediction model, constructing MJP-Law model to predict the sentence of legal cases.The HAN encoder in the model is utilized to extract the inter-sentence relations in the legal case and construct the relations among the law, the charge, and the sentence period.Compare the performance of this paper's MJP-Law model with other prediction models on law, charge, and sentence period, and explore the effects of the three subtasks of law, charge, and sentence period on the model through ablation experiments, and compare the prediction effects of a single MJP model and the MJP-Law model on low-frequency charges.In this paper, the MJP-Law model outperforms other prediction models in terms of prediction performance on statute, offense, and sentence.The four models of "MJP-Law", "MJP-Law_law", "MJP-Law_SG" and "MJP" had the same prediction performance, which were 95.54%, 89.86%, 89.73% and 89.81%, respectively."MJP-Law" and "MJP-Law_law", "MJP-Law_SG" and "MJP" have the same performance in law prediction.After removing the sentencing guidelines and legal sentences, the macro F1 values of the MJP-Law model all showed a decrease.The predictive performance of the MJP-Law model on low-frequency offenses was better than that of the single MJP model.
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 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 | 0.006 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".