The Role and Optimization of Multi-task Learning Models in Legal Decision Prediction
Bibliographic record
Abstract
Prediction of legal decisions using machine learning and artificial intelligence techniques has gradually become an important part of smart court technology.In addition the crime prediction and law recommendation also face the problem of easily confusing crimes.In order to solve these problems, this paper unites multi-task learning models and proposes a model fusion legal verdict prediction model.An attention neural network fusing Transformer Encoder and DPCNN encodes the key semantic information in the case description.The TF-IDF algorithm and TextRank algorithm are applied to extract the keywords of the charge, and the forward propagation network is used as a classifier to constitute a multi-task learning legal verdict prediction model.Using 9 2018 CAIL legal datasets as experimental data, the metrics performance of the multi-task learning legal judgment prediction model proposed in this paper is measured on three subtasks (offense prediction, legal provision prediction, and punishment duration prediction) in LJP.Combining real case information for legal verdict prediction as well as charge differentiation.The verdict prediction results on the CAIL-Big-Multi dataset show that the mean MP value of the comparison algorithms is 82.925% in the charge prediction.And the MP index of the charge prediction of the multitask learning legal verdict prediction model proposed in this paper is 89.13%, which is significantly higher than the mean value of the comparison algorithms.And the multitask learning model incorporating the keyword information of charges in case analysis can effectively solve the problem of confusing charges.
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 | 0.003 | 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 | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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 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".