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

Enhancing Court View Generation with Knowledge Injection and Guidance (2403.04366v1)

Published 7 Mar 2024 in cs.AI

Abstract: Court View Generation (CVG) is a challenging task in the field of Legal Artificial Intelligence (LegalAI), which aims to generate court views based on the plaintiff claims and the fact descriptions. While Pretrained LLMs (PLMs) have showcased their prowess in natural language generation, their application to the complex, knowledge-intensive domain of CVG often reveals inherent limitations. In this paper, we present a novel approach, named Knowledge Injection and Guidance (KIG), designed to bolster CVG using PLMs. To efficiently incorporate domain knowledge during the training stage, we introduce a knowledge-injected prompt encoder for prompt tuning, thereby reducing computational overhead. Moreover, to further enhance the model's ability to utilize domain knowledge, we employ a generating navigator, which dynamically guides the text generation process in the inference stage without altering the model's architecture, making it readily transferable. Comprehensive experiments on real-world data demonstrate the effectiveness of our approach compared to several established baselines, especially in the responsivity of claims, where it outperforms the best baseline by 11.87%.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Neural legal judgment prediction in english. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pages 4317–4323. Association for Computational Linguistics.
  2. Knowprompt: Knowledge-aware prompt-tuning with synergistic optimization for relation extraction. In Proceedings of the ACM Web Conference 2022, pages 2778–2788.
  3. 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), pages 648–664, Dublin, Ireland. Association for Computational Linguistics.
  4. Response generation with context-aware prompt learning. ArXiv, abs/2111.02643.
  5. How Can We Know What Language Models Know? Transactions of the Association for Computational Linguistics, 8:423–438.
  6. Ctrl: A conditional transformer language model for controllable generation.
  7. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461.
  8. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190.
  9. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81.
  10. P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602.
  11. Gpt understands, too. arXiv preprint arXiv:2103.10385.
  12. ML-LJP: multi-law aware legal judgment prediction. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023, Taipei, Taiwan, July 23-27, 2023, pages 1023–1034. ACM.
  13. Learning to predict charges for criminal cases with legal basis. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2727–2736, Copenhagen, Denmark. Association for Computational Linguistics.
  14. Large-scale multi-label text classification - revisiting neural networks. In Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2014, Nancy, France, September 15-19, 2014. Proceedings, Part II, volume 8725 of Lecture Notes in Computer Science, pages 437–452. Springer.
  15. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
  16. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1):5485–5551.
  17. Laria Reynolds and Kyle McDonell. 2021. Prompt programming for large language models: Beyond the few-shot paradigm.
  18. Get to the point: Summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368.
  19. Bert-pli: Modeling paragraph-level interactions for legal case retrieval. In International Joint Conference on Artificial Intelligence.
  20. Autoprompt: Eliciting knowledge from language models with automatically generated prompts.
  21. Attention is all you need. Advances in neural information processing systems, 30.
  22. Hierarchical matching network for crime classification. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019, Paris, France, July 21-25, 2019, pages 325–334. ACM.
  23. Modeling dynamic pairwise attention for crime classification over legal articles. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR 2018, Ann Arbor, MI, USA, July 08-12, 2018, pages 485–494. ACM.
  24. Community preserving network embedding. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI’17, page 203–209. AAAI Press.
  25. De-biased court’s view generation with causality. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 763–780.
  26. Precedent-enhanced legal judgment prediction with LLM and domain-model collaboration. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12060–12075, Singapore. Association for Computational Linguistics.
  27. Lawformer: A pre-trained language model for chinese legal long documents. AI Open, 2:79–84.
  28. Data-driven learning for data rights, data pricing, and privacy computing. Engineering, 25:66–76.
  29. Distinguish confusing law articles for legal judgment prediction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pages 3086–3095. Association for Computational Linguistics.
  30. Kevin Yang and Dan Klein. 2021. FUDGE: Controlled text generation with future discriminators. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics.
  31. Legal prompting: Teaching a language model to think like a lawyer.
  32. 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, pages 973–982.
  33. Circumstances enhanced criminal court view generation. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 1855–1859.
  34. Hanqing Zhang and Dawei Song. 2022. Discup: Discriminator cooperative unlikelihood prompt-tuning for controllable text generation.
  35. A survey of controllable text generation using transformer-based pre-trained language models.
  36. Dialogpt: Large-scale generative pre-training for conversational response generation.
  37. Legal judgment prediction via topological learning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3540–3549, Brussels, Belgium. Association for Computational Linguistics.
  38. Jec-qa: A legal-domain question answering dataset.
  39. 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. Association for Computational Linguistics.
  40. Fine-tuning language models from human preferences.
  41. Controllable generation from pre-trained language models via inverse prompting. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery Data Mining. ACM.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets