Exploring Lightweight Large Language Models for Court View Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hou, Zhitian, Hao, Tianyong, Zeng, Nanli, Chao, Zhixiong, Zeng, Kun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911690859216896
author Hou, Zhitian
Hao, Tianyong
Zeng, Nanli
Chao, Zhixiong
Zeng, Kun
author_facet Hou, Zhitian
Hao, Tianyong
Zeng, Nanli
Chao, Zhixiong
Zeng, Kun
contents Criminal Court View Generation (CVG) is a critical task in Legal Artificial Intelligence (Legal AI), involving the generation of court view based on case facts. In this work, we systematically explore the capabilities of lightweight (smaller than 2B) large language models (LLMs) in CVG and their impact on charge prediction. Our study addresses four key questions: (1) how does different architecture of LLMs affect the CVG quality and charge prediction. (2) how does LLMs size contribute to the performance, (3) how do lightweight LLMs compare with Deep Neural Networks (DNNs) in these tasks, and (4) how does predicting charge by court view generation first compare with predicting it directly. Additionally, we also develop CVGEvalKit, an evaluation framework including three public available datasets for CVG tasks, as well as predicting their charges. Comprehensive experiments are conducted on this framework, where models are trained on a mixed training set and evaluated on each dataset's test set. Experimental results provide new insights into the trade-offs between model architecture, model size, and the influence between different tasks, highlighting the potential of lightweight LLMs in judicial AI applications. The source code is anonymously available at \url{https://github.com/ZhitianHou/CVGEvalKit}
format Preprint
id arxiv_https___arxiv_org_abs_2605_16770
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Exploring Lightweight Large Language Models for Court View Generation
Hou, Zhitian
Hao, Tianyong
Zeng, Nanli
Chao, Zhixiong
Zeng, Kun
Computation and Language
Artificial Intelligence
Criminal Court View Generation (CVG) is a critical task in Legal Artificial Intelligence (Legal AI), involving the generation of court view based on case facts. In this work, we systematically explore the capabilities of lightweight (smaller than 2B) large language models (LLMs) in CVG and their impact on charge prediction. Our study addresses four key questions: (1) how does different architecture of LLMs affect the CVG quality and charge prediction. (2) how does LLMs size contribute to the performance, (3) how do lightweight LLMs compare with Deep Neural Networks (DNNs) in these tasks, and (4) how does predicting charge by court view generation first compare with predicting it directly. Additionally, we also develop CVGEvalKit, an evaluation framework including three public available datasets for CVG tasks, as well as predicting their charges. Comprehensive experiments are conducted on this framework, where models are trained on a mixed training set and evaluated on each dataset's test set. Experimental results provide new insights into the trade-offs between model architecture, model size, and the influence between different tasks, highlighting the potential of lightweight LLMs in judicial AI applications. The source code is anonymously available at \url{https://github.com/ZhitianHou/CVGEvalKit}
title Exploring Lightweight Large Language Models for Court View Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.16770