Skip to main content

Advertisement

Springer Nature Link
Log in

Prompt4LJP: prompt learning for legal judgment prediction

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

A Correction to this article was published on 01 April 2025

This article has been updated

Abstract

The task of legal judgment prediction (LJP) involves predicting court decisions based on the facts of the case, including identifying the applicable law article, the charge, and the term of penalty. While neural methods have made significant strides in this area, they often fail to fully harness the rich semantic potential of language models (LMs). Prompt learning is a novel paradigm in natural language processing (NLP) that reformulates downstream tasks into cloze-style or prefix-style prediction challenges by utilizing specialized prompt templates. This paradigm shows significant potential across various NLP domains, including short text classification. However, the dynamic word lengths of LJP labels present a challenge to the general prompt templates designed for single-word [MASK] tokens commonly used in many NLP tasks. To address this gap, we introduce the Prompt4LJP framework, a new method based on the prompt learning paradigm for the complex LJP task. Our framework employs a dual-slot prompt template in conjunction with a correlation scoring mechanism to maximize the utility of LMs without requiring additional resources or complex tokenization schemes. Specifically, the dual-slot template consists of two distinct slots: one dedicated to factual descriptions and the other to labels. This approach effectively tackles the challenge of dynamic word lengths in LJP labels, reformulating the LJP classification task as an evaluation of the applicability of each label. By incorporating a correlation scoring mechanism, we can identify the final result label. The experimental results show that our Prompt4LJP method, whether using discrete or continuous templates, outperforms baseline methods, particularly in charges and terms of penalty prediction. Compared to the best baseline model EPM, Prompt4LJP shows F1-score improvements of 2.25% and 4.76% (charge prediction and term of penalty prediction) with discrete templates, and 3.24% and 4.05% with the continuous template, demonstrating prompt4LJP ability to leverage pretrained knowledge and adapt flexibly to specific tasks. The source code can be obtained from https://github.com/huangqiongyannn/Prompt4LJP.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Data availability

No datasets were generated or analyzed during the current study.

Change history

  • 02 April 2025

    The original online version of this article was revised: " an affiliation has been added to Hui Fang, Yin Guan, and Ge Xu. Acknowlegments section has been added.

  • 01 April 2025

    A Correction to this paper has been published: https://doi.org/10.1007/s11227-025-07090-4

Notes

  1. http://data.court.gov.cn/pages/laic2021.html

References

  1. Luo B, Feng Y, Xu J, Zhang X, Zhao D (2017) Learning to predict charges for criminal cases with legal basis. arXiv preprint arXiv:1707.09168

  2. Feng Y, Li C, Ng V (2022) Legal judgment prediction via event extraction with constraints. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 648–664

  3. Zhang H, Dou Z, Zhu Y, Wen J-R (2023) Contrastive learning for legal judgment prediction. ACM Trans Inf Syst 41(4):1–25

    MATH  Google Scholar 

  4. Fei Z, Shen X, Zhu D, Zhou F, Han Z, Zhang S, Chen K, Shen Z, Ge J (2023) Lawbench: Benchmarking legal knowledge of large language models. arXiv preprint arXiv:2309.16289

  5. Schick T, Schütze H (2020) Exploiting cloze questions for few shot text classification and natural language inference. arXiv preprint arXiv:2001.07676

  6. Zhu Y, Wang Y, Qiang J, Wu X (2023) Prompt-learning for short text classification. IEEE Trans Knowl Data Eng 36:5328–5339

    MATH  Google Scholar 

  7. Wang C, Wang J, Qiu M, Huang J, Gao M (2021) Transprompt: Towards an automatic transferable prompting framework for few-shot text classification. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 2792–2802

  8. Zhang Z, Wang B (2023) Prompt learning for news recommendation. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 227–237

  9. Ding N, Chen Y, Han X, Xu G, Xie P, Zheng H-T, Liu Z, Li J, Kim H-G (2021) Prompt-learning for fine-grained entity typing. arXiv preprint arXiv:2108.10604

  10. Zhu T, Qin Y, Chen Q, Hu B, Xiang Y (2022) Enhancing entity representations with prompt learning for biomedical entity linking. In: IJCAI, pp. 4036–4042

  11. Xiang W, Wang Z, Dai L, Wang B (2022) Connprompt: Connective-cloze prompt learning for implicit discourse relation recognition. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 902–911

  12. Sahoo P, Singh AK, Saha S, Jain V, Mondal S, Chadha A (2024) A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv preprint arXiv:2402.07927

  13. Sabbatella A, Ponti A, Giordani I, Candelieri A, Archetti F (2024) Prompt optimization in large language models. Mathematics 12(6):929

    MATH  Google Scholar 

  14. Xiao C, Zhong H, Guo Z, Tu C, Liu Z, Sun M, Feng Y, Han X, Hu Z, Wang H, et al. (2018) Cail2018: A large-scale legal dataset for judgment prediction. arXiv preprint arXiv:1807.02478

  15. Kort F (1957) Predicting supreme court decisions mathematically: a quantitative analysis of the right to counsel cases. Am Polit Sci Rev 51(1):1–12

    MATH  Google Scholar 

  16. Segal JA (1984) Predicting supreme court cases probabilistically: the search and seizure cases, 1962–1981. Am Polit Sci Rev 78(4):891–900

    MATH  Google Scholar 

  17. Ulmer SS (1963) Quantitative analysis of judicial processes: some practical and theoretical applications. Law Contemp Probl 28(1):164–184

    MATH  Google Scholar 

  18. Zhong H, Guo Z, Tu C, Xiao C, Liu Z, Sun M (2018) Legal judgment prediction via topological learning. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3540–3549

  19. Yang W, Jia W, Zhou X, Luo Y (2019) Legal judgment prediction via multi-perspective bi-feedback network. arXiv preprint arXiv:1905.03969

  20. Xu N, Wang P, Chen L, Pan L, Wang X, Zhao J (2020) Distinguish confusing law articles for legal judgment prediction. arXiv preprint arXiv:2004.02557

  21. Yue L, Liu Q, Jin B, Wu H, Zhang K, An Y, Cheng M, Yin B, Wu D (2021) Neurjudge: A circumstance-aware neural framework for legal judgment prediction. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 973–982

  22. Liu Y, Wu Y, Zhang Y, Sun C, Lu W, Wu F, Kuang K (2023) Ml-ljp: Multi-law aware legal judgment prediction. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1023–1034

  23. Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805

  24. Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877–1901

    Google Scholar 

  25. Sun J, Huang S, Wei C (2024) Chinese legal judgment prediction via knowledgeable prompt learning. Expert Syst Appl 238:122177

    Google Scholar 

  26. Rubinstein RY, Kroese DP (2004) The cross-entropy method: a Unified approach to combinatorial Optimization, Monte-Carlo Simulation, and Machine Learning. Springer, New York

    MATH  Google Scholar 

  27. Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101

  28. Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, Cistac P, Rault T, Louf R, Funtowicz M, et al (2020) Transformers: State-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45

  29. Bai J, Bai S, Chu Y, Cui Z, Dang K, Deng X, Fan Y, Ge W, Han Y, Huang F, Hui B, Ji L, Li M, Lin J, Lin R, Liu D, Liu G, Lu C, Lu K, Ma J, Men R, Ren X, Ren X, Tan C, Tan S, Tu J, Wang P, Wang S, Wang W, Wu S, Xu B, Xu J, Yang A, Yang H, Yang J, Yang S, Yao Y, Yu B, Yuan H, Yuan Z, Zhang J, Zhang X, Zhang Y, Zhang Z, Zhou C, Zhou J, Zhou X, Zhu T (2023) Qwen technical report. arXiv preprint arXiv:2309.16609

  30. Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2021) Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685

  31. Zheng Y, Zhang R, Zhang J, Ye Y, Luo Z, Ma Y (2024) Llamafactory: Unified efficient fine-tuning of 100+ language models. arXiv preprint arXiv:2403.13372

Download references

Acknowledgments

This research was supported by the Fuzhou Science and Technology Major Special Project 'Open bidding for selecting the best candidates' Initiative (AFZ2024FZZD01080003), Minjiang University 'Open bidding for selecting the best candidates' Project (ZD202401), Minjiang University Introduced Talents Science and Technology Pre-research Project (MJY23033), Minjiang University Introduced Talents Science and Technology Pre-research Project (MJY21032), Fuzhou Marine Research Institute 'Open bidding for selecting the best candidates' Project (2024F02), and Fujian Province Middle-aged and Young Teachers Education and Scientific Research Project (Science and Technology Category) (JAT231095).

Author information

Author notes

  1. Y. Guan and G. Xu have contributed equally to this work.

Authors and Affiliations

  1. College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou, 350100, Fujian, China

    Qiongyan Huang & Ruiwei Liang

  2. School of Computer and Big Data, Minjiang University, Fuzhou, 350108, Fujian, China

    Hui Fang, Yin Guan & Ge Xu

  3. Fujian Mental Health Human-Computer Interaction Technology Research Center, Minjiang University, Fuzhou, 350108, Fujian, China

    Hui Fang, Yin Guan & Ge Xu

  4. School of Computer Science and Electronic Engineering, University of Essex, Colchester, Essex, CO4 3SQ, UK

    Yuhan Xia & Yunfei Long

  5. Fuzhou Institute of Oceanography, Fuzhou, 350108, Fujian, China

    Hui Fang, Yin Guan & Ge Xu

Authors
  1. Qiongyan Huang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yuhan Xia
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yunfei Long
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Hui Fang
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Ruiwei Liang
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Yin Guan
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Ge Xu
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Q.H. was responsible for the experimental design, data collection and analysis, and drafting the manuscript. Y.X. and Y.L. contributed to supplementing the experiments, refining experimental details, and revising and editing the initial manuscript. H.F., Y.G., and G.X. primarily focused on in-depth revisions of the initial manuscript, providing key feedback and suggestions, and improving the overall content. R.L. was responsible for conducting the supplementary experiments.

Corresponding author

Correspondence to Hui Fang.

Ethics declarations

Conflict of interest

The authors declare that they have no Conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

In this article, there were errors in Tables 8 and 10: Table 8: The asterisk (*) was incorrectly placed on the results for the “Discrete” and “Continuous” models. These results were obtained from our own experiments and should not have been marked as sourced from ML-LJP. The corrected version of the table removes the asterisks from these two models. Table 10: The formatting of the table was incorrect, causing misalignment of data in certain rows. The corrected table ensures proper alignment for improved clarity. The original article has been corrected.

The original online version of this article was revised: " an affiliation has been added to Hui Fang, Yin Guan, and Ge Xu. Acknowlegments section has been added.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Huang, Q., Xia, Y., Long, Y. et al. Prompt4LJP: prompt learning for legal judgment prediction. J Supercomput 81, 420 (2025). https://doi.org/10.1007/s11227-025-06945-0

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-025-06945-0

Keywords