Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

LegalDuet: Learning Effective Representations for Legal Judgment Prediction through a Dual-View Legal Clue Reasoning (2401.15371v2)

Published 27 Jan 2024 in cs.CL

Abstract: Most existing Legal Judgment Prediction (LJP) models focus on discovering the legal triggers in the criminal fact description. However, in real-world scenarios, a professional judge not only needs to assimilate the law case experience that thrives on past sentenced legal judgments but also depends on the professional legal grounded reasoning that learned from professional legal knowledge. In this paper, we propose a LegalDuet model, which pretrains LLMs to learn a tailored embedding space for making legal judgments. It proposes a dual-view legal clue reasoning mechanism, which derives from two reasoning chains of judges: 1) Law Case Reasoning, which makes legal judgments according to the judgment experiences learned from analogy/confusing legal cases; 2) Legal Ground Reasoning, which lies in matching the legal clues between criminal cases and legal decisions. Our experiments show that LegalDuet achieves state-of-the-art performance on the CAIL2018 dataset and outperforms baselines with about 4% improvements on average. Our dual-view reasoning based pretraining can capture critical legal clues to learn a tailored embedding space to distinguish criminal cases. It reduces LegalDuet's uncertainty during prediction and brings pretraining advances to the confusing/low frequent charges. All codes are available at https://github.com/NEUIR/LegalDuet.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. Kevin D. Ashley. 1991. Modeling legal argument - reasoning with cases and hypotheticals. In Artificial intelligence and legal reasoning.
  2. Katie Atkinson and Trevor Bench-Capon. 2005. Legal case-based reasoning as practical reasoning. Artificial Intelligence and Law.
  3. LEGAL-BERT: The muppets straight out of law school. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2898–2904.
  4. Syllogistic reasoning for legal judgment analysis. In Proceedings of EMNLP.
  5. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, pages 4171–4186.
  6. Qian Dong and Shuzi Niu. 2021. Legal judgment prediction via relational learning. In Proceedings of SIGIR, pages 983–992.
  7. Cert: Contrastive self-supervised learning for language understanding. ArXiv preprint, abs/2005.12766.
  8. Legal judgment prediction: A survey of the state of the art. In Proceedings of IJCAI, pages 5461–5469.
  9. Legal judgment prediction via event extraction with constraints. In Proceedings of ACL, pages 648–664.
  10. Judgment prediction via injecting legal knowledge into neural networks. pages 12866–12874.
  11. Exploiting contrastive learning and numerical evidence for confusing legal judgment prediction. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12174–12185.
  12. SimCSE: Simple contrastive learning of sentence embeddings. In Proceedings of EMNLP, pages 6894–6910.
  13. Learning fine-grained fact-article correspondence in legal cases. IEEE/ACM Trans. Audio, Speech and Lang. Proceedings.
  14. Don’t stop pretraining: Adapt language models to domains and tasks. In Proceedings of ACL, pages 8342–8360.
  15. Computer power and legal reasoning: A case study of judicial decision prediction in zoning amendment cases. American Bar Foundation Research Journal.
  16. Inductive representation learning on large graphs. In proceedings of NeurIPS, pages 1024–1034.
  17. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Comput.
  18. Few-shot charge prediction with discriminative legal attributes. In Proceedings of COLING, pages 487–498.
  19. Rie Johnson and Tong Zhang. 2017. Deep pyramid convolutional neural networks for text categorization. In Proceedings of ACL, pages 562–570.
  20. Dense passage retrieval for open-domain question answering. In Proceedings of EMNLP, pages 6769–6781.
  21. Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of EMNLP, pages 1746–1751.
  22. Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR.
  23. BENJAMIN E. LAUDERDALE and TOM S. CLARK. 2012. The supreme court’s many median justices. The American Political Science Review.
  24. Edward Hirsch Levi. 1950. An introduction to legal reasoning.
  25. Sailer: Structure-aware pre-trained language model for legal case retrieval. In Proceedings of SIGIR, page 1035–1044.
  26. Text-guided legal knowledge graph reasoning. ArXiv preprint, abs/2104.02284.
  27. Augmenting legal judgment prediction with contrastive case relations. In Proceedings of COLING, pages 2658–2667.
  28. Ml-ljp: Multi-law aware legal judgment prediction. In Proceedings of AAAI, page 1023–1034.
  29. Roberta: A robustly optimized bert pretraining approach. ArXiv preprint, abs/1907.11692.
  30. Fine-grained fact verification with kernel graph attention network. In Proceedings of ACL, pages 7342–7351.
  31. Dimension reduction for efficient dense retrieval via conditional autoencoder. In Proceedings of EMNLP, pages 5692–5698.
  32. Zhenyu Liu and Huanhuan Chen. 2017. A predictive performance comparison of machine learning models for judicial cases. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pages 1–6.
  33. Legal judgment prediction with multi-stage case representation learning in the real court setting. In Proceedings of SIGIR, page 993–1002.
  34. Caseencoder: A knowledge-enhanced pre-trained model for legal case encoding. ArXiv preprint, abs/2305.05393.
  35. Henry Pinkard and Laura Waller. 2022. A visual introduction to information theory. ArXiv preprint, abs/2206.07867.
  36. Gerard Salton and Christopher Buckley. 1988. Term-weighting approaches in automatic text retrieval. Information Processing & Management, (5):513–523.
  37. Improving legal information retrieval using an ontological framework. Artificial Intelligence and Law.
  38. BERT-PLI: modeling paragraph-level interactions for legal case retrieval. In proceedings of IJCAI.
  39. Law article-enhanced legal case matching: A causal learning approach. In Proceedings of SIGIR, page 1549–1558.
  40. Attention is all you need. In proceedings of NeurIPS, pages 5998–6008.
  41. Graph attention networks. In Proceedings of ICLR.
  42. Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In Proceedings of ICML.
  43. Towards interactivity and interpretability: A rationale-based legal judgment prediction framework. In Proceedings of EMNLP, pages 4787–4799.
  44. Clear: Contrastive learning for sentence representation. ArXiv preprint, abs/2012.15466.
  45. Lawformer: A pre-trained language model for chinese legal long documents. AI Open, 2:79–84.
  46. Legal Knowledge Representation Learning, pages 401–432.
  47. Cail2018: A large-scale legal dataset for judgment prediction. ArXiv preprint.
  48. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In Proceedings of ICLR.
  49. Distinguish confusing law articles for legal judgment prediction. In Proceedings of ACL, pages 3086–3095.
  50. ConSERT: A contrastive framework for self-supervised sentence representation transfer. In Proceedings of ACL, pages 5065–5075.
  51. Legal judgment prediction via multi-perspective bi-feedback network. In Proceedings of IJCAI, pages 4085–4091.
  52. Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions. In Proceedings of NAACL-HLT, pages 1854–1864.
  53. Neurjudge: A circumstance-aware neural framework for legal judgment prediction. In Proceedings of SIGIR, pages 973–982.
  54. Barlow twins: Self-supervised learning via redundancy reduction. In Proceedings of ICML, pages 12310–12320.
  55. Knowledge representation for the intelligent legal case retrieval. In Proceedings of the 9th International Conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part I, page 339–345.
  56. Contrastive learning for legal judgment prediction. ACM Trans. Inf. Syst.
  57. Transformer-xh: Multi-evidence reasoning with extra hop attention. In Proceedings of ICLR.
  58. Legal judgment prediction via topological learning. In Proceedings of EMNLP, pages 3540–3549.
  59. How does NLP benefit legal system: A summary of legal artificial intelligence. In Proceedings of ACL, pages 5218–5230.
  60. Open chinese language pre-trained model zoo. Technical report.
  61. GEAR: Graph-based evidence aggregating and reasoning for fact verification. In Proceedings of ACL, pages 892–901.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Pengjie Liu (5 papers)
  2. Zhenghao Liu (77 papers)
  3. Xiaoyuan Yi (42 papers)
  4. Liner Yang (22 papers)
  5. Shuo Wang (382 papers)
  6. Yu Gu (218 papers)
  7. Ge Yu (63 papers)
  8. Xing Xie (220 papers)
  9. Shuang-Hua Yang (15 papers)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets