Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914902456664064 |
|---|---|
| author | Deng, Chenlong Mao, Kelong Zhang, Yuyao Dou, Zhicheng |
| author_facet | Deng, Chenlong Mao, Kelong Zhang, Yuyao Dou, Zhicheng |
| contents | Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to challenges in understanding case complexities and distinguishing between similar charges. To adapt LLMs for effective legal judgment prediction, we introduce the Ask-Discriminate-Predict (ADAPT) reasoning framework inspired by human judicial reasoning. ADAPT involves decomposing case facts, discriminating among potential charges, and predicting the final judgment. We further enhance LLMs through fine-tuning with multi-task synthetic trajectories to improve legal judgment prediction accuracy and efficiency under our ADAPT framework. Extensive experiments conducted on two widely-used datasets demonstrate the superior performance of our framework in legal judgment prediction, particularly when dealing with complex and confusing charges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01964 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction Deng, Chenlong Mao, Kelong Zhang, Yuyao Dou, Zhicheng Computation and Language Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to challenges in understanding case complexities and distinguishing between similar charges. To adapt LLMs for effective legal judgment prediction, we introduce the Ask-Discriminate-Predict (ADAPT) reasoning framework inspired by human judicial reasoning. ADAPT involves decomposing case facts, discriminating among potential charges, and predicting the final judgment. We further enhance LLMs through fine-tuning with multi-task synthetic trajectories to improve legal judgment prediction accuracy and efficiency under our ADAPT framework. Extensive experiments conducted on two widely-used datasets demonstrate the superior performance of our framework in legal judgment prediction, particularly when dealing with complex and confusing charges. |
| title | Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.01964 |