Legal judgment prediction via dynamic task graph and keyword-aware contrastive learning
Jiawei Li, Shengjia Zhang · 2026
Read Legal judgment prediction via dynamic task graph and keyword-aware contrastive learning by Jiawei Li, Shengjia Zhang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13561339.txt.
Description
Jiawei Li and Shengjia Zhang build a model that predicts court judgments from case facts with linked subtasks. Judgment prediction must output charges, legal articles, and penalty terms. These outputs depend on each other in structured ways.
Case texts also carry keyword clues that older methods waste. Their framework builds a task graph that shifts per case. Graph convolution then encodes how subtasks relate for that case. A keyword fusion step sharpens charge distinctions that often confuse models. Contrastive learning with keyword awareness adds further separation. The design targets crimes with similar fact patterns. Tests weigh the gains of each added part. The work advances automated legal analysis tools.
Catalog record
| CREATOR | Jiawei Li, Shengjia Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |