法律判決預測（LJP）旨在基於案件之犯罪事實以預測判決結果（如法條、罪名和刑期）。這個領域大多相關研究都是基於法院判決書中所記載之犯罪事實所為模型之犯罪事實輸入。然而，每個判決書所記載之犯罪事實內容實際上都是基於起訴書的內容做延伸。除此外，過去相關研究之目的大多致力於服務法官，作為其工作上之輔助工具。然而實務上有更多的需求來自於檢察官起訴案件後，案件是否會被法官駁回或是法官不受理？如果被告無受法官處罰，則原因為何？若有處罰，則是受到有期徒刑還是罰款之處罰？是違反了哪一條法條與罪名？因此，在這項研究中，我們定義了三個新穎之LJP任務，分別為檢察官提供協助，包括起訴結果預測（LJP\#1）、刑事罰款預測（LJP\#2）和刑事刑期預測（LJP\#3）。

本篇之研究係基於多任務學習(Multi-task Learning)架構，而在上述每個工作中之子任務間亦是具有相依關係，換言之，一項子任務之預測結果也影響了其他子任務之預測結果。在本篇論文中，對於子任務之間應用了不同之拓譜架構如IMN(Iteracitve Message Passing Network)及TopJudge與本篇研究提出結合IMN與TopJudge形成之拓譜架構並搭配不同之語言模型，如Word2Vec、BERT、Lawformer 進行LJP任務，比較子任務形成不同之拓譜架構並應用不同之語言模型對於效能之影響。此外，由於大型語言模型中的參數數量巨大，對每個LJP任務進行Full-Tuning的成本將變得越來越昂貴。為解決這個問題，我們採用了LoRA(Low-Rank Adaptation)架構，這是屬於一種Parameter-Efficient Fine-Tuning(PEFT)的技術，以減少訓練參數數量並節省計算成本與模型訓練時間。實驗結果顯示，使用LoRA進行Fine-Tuning不僅降低了訓練時間（45\%），甚至對某些LJP任務帶來了性能提升效果（2.5\%的Macro F1）。

Legal Judgment Prediction (LJP) aims to predict the judgement results (such as article, charge, and penalty) based on the criminal facts of the case. Most previous research in this field was based on criminal statements from court verdicts. However, each verdict actually is based on the content from indictments. For prosecutors, will the case be dismissed or processed? If the case is accepted, is the penalty a jail sentence or a fine? What is the charge and article violated? In this study, we therefore define three novel LJP tasks for prosecutors, including prosecution outcome prediction (LJP\#1), fine prediction (LJP\#2) and imprison prediction (LJP\#3).
Due to the huge number of parameters in a large language model, the cost of full-tuning for each LJP task will become increasingly expensive.
To solve this problem, we adopt the LoRA (Low-Rank Adaptation) architecture, a technique for parameter-efficient fine-tuning (PEFT) to reduce the number of tuned parameters and save computational cost/time. The experiments show that using LoRA for fine-tuning not only improves not only reduce training time (45\%) but also brings performance improvement effect (2.5\% F1) for some LJP tasks.

[1] Haoxi Zhong, Zhipeng Guo, Cunchao Tu, Chaojun Xiao, Zhiyuan Liu, and Maosong Sun. Legal judgment prediction via topological learning. In Proceedings of the 2018 Conference on Empirical Meth- ods in Natural Language Processing, pages 3540–3549, Brussels, Bel- gium, October-November 2018. Association for Computational Lin- guistics.
[2] Ruidan He, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. An interactive multi-task learning network for end-to-end aspect-based sentiment analysis. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 504–515, Florence, Italy, July 2019. Association for Computational Linguistics.
[3] Chaojun Xiao, Haoxi Zhong, Zhipeng Guo, Cunchao Tu, Zhiyuan Liu, Maosong Sun, Yansong Feng, Xianpei Han, Zhen Hu, Heng Wang, and Jianfeng Xu. Cail2018: A large-scale legal dataset for judgment prediction, 2018.
[4] Xuanwei Zhang and Liang Xu. Promptclue: A zero-shot learning model that supports full chinese tasks, September 2022.
[5] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota, June 2019. Association for Computational Linguistics.
[6] Haoxi Zhong, Chaojun Xiao, Cunchao Tu, Tianyang Zhang, Zhiyuan Liu, and Maosong Sun. How does NLP benefit legal system: A summary of legal artificial intelligence. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5218–5230, Online, July 2020. Association for Computational Linguistics.
[7] Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, and Sayak Paul. Peft: State-of-the-art parameter-efficient fine-tuning methods. https://github.com/huggingface/peft, 2022.
[8] Junyun Cui, Xiaoyu Shen, Feiping Nie, Zheng Wang, Jinglong Wang, and Yulong Chen. A survey on legal judgment prediction: Datasets, metrics, models and challenges, 2022.