Elamur Research⌕
☰
home / papers / 2026 / LegalChainReasoner: Grounding Criminal Judicial Opinion Generation via Structured Legal Chains

LegalChainReasoner: Grounding Criminal Judicial Opinion Generation via Structured Legal Chains

Paper · 2026 · Weizhe Shi, Qiqi Wang, Yihong Pan et al.

Summary

Current LegalAI work treats legal reasoning and sentencing prediction as separate tasks. As a result, generated arguments can contradict the predicted penalty, and predicted sentences come with no legal justification. The authors propose a new task, Criminal Judicial Opinion Generation (CJOG), in which a model writes the rationale and the sentencing decision together, given the case facts and the charge.

Their framework, LegalChainReasoner, rests on Legal Norm theory. An LLM, prompted under constraints, automatically breaks statutory provisions into premise–situation–conclusion triplets called Legal Chains, which legal experts then check. A Chain-Aware Encoding module embeds these chains, models how their components relate, and applies charge-specific transformations. The resulting legal representations are fused with case-fact embeddings inside the LLM.

On open Chinese criminal-case data, the method beats the baselines in both opinion quality and sentencing accuracy, on the joint task and on each subtask alone. This matters because it brings automated judicial support closer to real court practice, where a sentence must follow from explicit legal reasoning, and it avoids costly manually built knowledge.

Key points

  • The CJOG task assumes the charge is given, since prior work already reports over 95% accuracy on charge prediction.
  • Each Legal Chain is a triplet ⟨premise, situation, conclusion⟩ extracted from statutes by prompting an LLM and validated by experts. Each component is embedded by mean pooling, which beat the alternative strategies tested, and then processed with multi-head attention and multi-linear layers.
  • Cases come from China Judgment Online and the People's Court Case Database, with personal data anonymized. Code and data are released on GitHub (Statistical-NLP-Lab/LegalChainReasoner).
  • Baselines in the case study include AttS2S, BART, Lawyer-Llama-13B-V2 and a variant given raw statutory provisions. LegalChainReasoner kept facts, reasoning and sentence most consistent, and its remaining errors are attributed to gaps in chain coverage rather than hallucination.
  • Evaluation relies on LLM judging and a combined accuracy over three equally weighted parts: defendant identification, situation description and sentencing range. The authors flag both as limitations, along with the time-bound nature of the data.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Harbin Institute of TechnologyHarbin · China158 works · 28,841 citations🎓University of AucklandAuckland · New Zealand11 works · 888 citations🎓Nankai UniversityTianjin · China24 works · 762 citations

 Fields, topics and concepts

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksSocial Sciences · 1,772 worksPolitical Science and International Relations · 182 worksLaw · 77 works

🧭 Topics 1Research subjects and languages the work is about.Legal AI · 134 works

Cite

Cite as Weizhe Shi, Qiqi Wang, Yihong Pan, Qian Liu and Kaiqi Zhao. 2026. LegalChainReasoner: Grounding Criminal Judicial Opinion Generation via Structured Legal Chains. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.1093

@inproceedings{shi2026legalchainreasoner,
  title = {{LegalChainReasoner: Grounding Criminal Judicial Opinion Generation via Structured Legal Chains}},
  author = {Weizhe Shi, Qiqi Wang, Yihong Pan, Qian Liu and Kaiqi Zhao},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1093},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1093}
}

References

50 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. ↗
  2. Weilin Cai, Juyong Jiang, Fan Wang, Jing Tang, Sunghun Kim, and Jiayi Huang. 2025. A survey on mixture of experts in large language models. IEEE Trans. Knowl. Data Eng., 37(7):3896–3915. ↗
  3. Ilias Chalkidis, Ion Androutsopoulos, and Nikolaos Aletras. 2019. 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. ACL.
  4. Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: pre-training text encoders as discriminators rather than generators. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. of the 31st International Conference on Computational Linguistics, COLING 2025, Abu Dhabi, UAE, January 19-24, 2025, pages 10738–10766. ACL. find
  5. Chenlong Deng, Kelong Mao, Yuyao Zhang, and Zhicheng Dou. 2024. Enabling discriminative reasoning in llms for legal judgment prediction. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, Findings of ACL, pages 784–796. ACL. find
  6. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. 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 Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pages 4171–4186. ACL.
  7. Qian Dong and Shuzi Niu. 2021. Legal judgment prediction via relational learning. In SIGIR ’21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021, pages 983–992. ACM. find
  8. Jinlan Fu, See-Kiong Ng, Zhengbao Jiang, and Pengfei Liu. 2024. Gptscore: Evaluate as you desire. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2024, Mexico City, Mexico, June 16-21, 2024, pages 6556–6576. ACL. ↗
  9. Leilei Gan, Kun Kuang, Yi Yang, and Fei Wu. 2021. Judgment prediction via injecting legal knowledge into neural networks. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pages 12866–12874. AAAI Press. find
  10. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. Lora: Low-rank adaptation of large language models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net.
  11. Junyun Cui, Xiaoyu Shen, and Shaochun Wen. 2023. A survey on legal judgment prediction: Datasets, metrics, models and challenges. IEEE Access, 11:102050–102071. ↗
  12. Zikun Hu, Xiang Li, Cunchao Tu, Zhiyuan Liu, and Maosong Sun. 2018. Few-shot charge prediction with discriminative legal attributes. In Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018, pages 487–498. ACL.
  13. Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, and Hao Wang. 2025. Laiw: A chinese legal large language models benchmark. In Proceedings Quzhe Huang, Mingxu Tao, Zhenwei An, Chen Zhang, Cong Jiang, Zhibin Chen, Zirui Wu, and Yansong Feng. 2023. Lawyer llama technical report. CoRR, abs/2305.15062. ↗
  14. Herbert Keuth. 1975. On some logical characteristics of legal norms. Jurimetrics Journal, 15(3):160–170. Legal knowledge infusion for large language models: A survey. Inf. Fusion, 125:103426. find
  15. Yuquan Le, Congqing He, Meng Chen, Youzheng Wu, Xiaodong He, and Bowen Zhou. 2020. Learning to predict charges for legal judgment via self-attentive capsule network. In ECAI 2020 - 24th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29 - September 8, 2020 - Including 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020), Frontiers in Artificial Intelligence and Applications, pages 1802–1809. IOS Press. ↗
  16. Yifei Liu, Yiquan Wu, Yating Zhang, Changlong Sun, Weiming Lu, Fei Wu, and Kun Kuang. 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, SIGIR 2023, Taipei, Taiwan, July 23-27, 2023, pages 1023–1034. ACM. find
  17. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pages 7871–7880. ACL.
  18. Ang Li, Yiquan Wu, Ming Cai, Adam Jatowt, Xiang Zhou, Weiming Lu, Changlong Sun, Fei Wu, and Kun Kuang. 2025. Legal judgment prediction based on knowledge-enhanced multi-task and multi-label text classification. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2025 - Volume 1: Long Papers, Albuquerque, New Mexico, USA, April 29 - May 4, 2025, pages 6957–6970. ACL. find
  19. Ang Li, Yiquan Wu, Yifei Liu, Kun Kuang, Fei Wu, and Ming Cai. 2024a. Enhancing court view generation with knowledge injection and guidance. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC/COLING 2024, 20-25 May, 2024, Torino, Italy, pages 5896–5906. ELRA and ICCL. find
  20. Zhen Li, Xiaohan Xu, Tao Shen, Can Xu, Jia-Chen Gu, Yuxuan Lai, Chongyang Tao, and Shuai Ma. 2024b. Leveraging large language models for NLG evaluation: Advances and challenges. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Miami, FL, USA, November 12-16, 2024, pages 16028–16045. ACL.
  21. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81. ACL.
  22. Dugang Liu, Weihao Du, Lei Li, Weike Pan, and Zhong Ming. 2022. Augmenting legal judgment prediction with contrastive case relations. In Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12-17, 2022, pages 2658–2667. ICCL. find
  23. Qian Liu, Hang Yu, Qiqi Wang, Qi Xu, Jinpeng Li, Zhuoqun Zou, Rui Mao, and Erik Cambria. 2026. find
  24. Saeed Masoudnia and Reza Ebrahimpour. 2014. Mixture of experts: a literature survey. Artif. Intell. Rev., 42(2):275–293. find
  25. Chunyun Meng, Yuki Todo, Cheng Tang, Li Luan, and Zheng Tang. 2025. DPFSI: A legal judgment prediction method based on deontic logic prompt and fusion of law article statistical information. Expert Syst. Appl., 272:126722. ↗
  26. Venkatesh Mishra, Bimsara Pathiraja, Mihir Parmar, Sat Chidananda, Jayanth Srinivasa, Gaowen Liu, Ali Payani, and Chitta Baral. 2025. Investigating the shortcomings of llms in step-by-step legal reasoning. In Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29 - May 4, 2025, Findings of ACL, pages 7795–7826. ACL. find
  27. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, July 6-12, 2002, Philadelphia, PA, USA, pages 311–318. ACL.
  28. Joseph Raz. 1980. The Concept of a Legal System: An Introduction to the Theory of a Legal System. Oxford University Press. find
  29. Jingyun Sun, Shaobin Huang, and Chi Wei. 2024. Chinese legal judgment prediction via knowledgeable prompt learning. Expert Syst. Appl., 238(Part E):122177. ↗
  30. DeepSeek-AI Team. 2025. Deepseek-r1 incentivizes reasoning in llms through reinforcement learning. Nat., 645(8081):633–638. find
  31. Llama Team. 2024a. The llama 3 herd of models. CoRR, abs/2407.21783. ↗
  32. Qwen Team. 2024b. Qwen2.5 technical report. CoRR, abs/2412.15115. ↗
  33. Qiqi Wang, Ruofan Wang, Kaiqi Zhao, Robert Amor, Benjamin Liu, Xianda Zheng, Zeyu Zhang, and Zijian Huang. 2023. Towards legal judgment summarization: A structure-enhanced approach. In ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems (PAIS 2023), Frontiers in Artificial Intelligence and Applications, pages 2491–2498. IOS Press. ↗
  34. Yiquan Wu, Kun Kuang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Jun Xiao, Yueting Zhuang, Luo Si, and Fei Wu. 2020. De-biased court’s view generation with causality. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pages 763–780. ACL. find
  35. Yiquan Wu, Yifei Liu, Weiming Lu, Yating Zhang, Jun Feng, Changlong Sun, Fei Wu, and Kun Kuang. 2022. Towards interactivity and interpretability: A rationale-based legal judgment prediction framework. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, pages 4787–4799. ACL. find
  36. Yiquan Wu, Siying Zhou, Yifei Liu, Weiming Lu, Xiaozhong Liu, Yating Zhang, Changlong Sun, Fei Wu, and Kun Kuang. 2023. Precedent-enhanced legal judgment prediction with LLM and domain-model collaboration. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 12060–12075. ACL. ↗
  37. Chunyu Xia, Tieke He, Wenlong Li, Zemin Qin, and Zhipeng Zou. 2019. Similarity analysis of law documents based on word2vec. In 19th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS Companion 2019, Sofia, Bulgaria, July 22-26, 2019, pages 354–357. IEEE. find
  38. Chaojun Xiao, Haoxi Zhong, Zhipeng Guo, Cunchao Tu, Zhiyuan Liu, Maosong Sun, Yansong Feng, Xianpei Han, Zhen Hu, Heng Wang, and Jianfeng Xu. 2018. CAIL2018: A large-scale legal dataset for judgment prediction. CoRR, abs/1807.02478. ↗
  39. Nuo Xu, Pinghui Wang, Long Chen, Li Pan, Xiaoyan Wang, and Junzhou Zhao. 2020. 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. ACL.
  40. Qi Xu, Xiao Wei, Hang Yu, Qian Liu, and Hao Fei. 2024. Divide and conquer: Legal concept-guided criminal court view generation. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, Findings of ACL, pages 3395–3410. ACL. find
  41. Jun Yang, Weizhi Ma, Min Zhang, Xin Zhou, Yiqun Liu, and Shaoping Ma. 2022. Legalgnn: Legal information enhanced graph neural network for recommendation. ACM Trans. Inf. Syst., 40(2):33:1–33:29. ↗
  42. Hai Ye, Xin Jiang, Zhunchen Luo, and Wenhan Chao. 2018. Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 1 (Long Papers), pages 1854–1864. ACL. ↗
  43. Linan Yue, Qi Liu, Binbin Jin, Han Wu, Kai Zhang, Yanqing An, Mingyue Cheng, Biao Yin, and Dayong Wu. 2021a. Neurjudge: A circumstance-aware neural framework for legal judgment prediction. In SIGIR ’21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021, pages 973–982. ACM. find
  44. Linan Yue, Qi Liu, Han Wu, Yanqing An, Li Wang, Senchao Yuan, and Dayong Wu. 2021b. Circumstances enhanced criminal court view generation. In SIGIR ’21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021, pages 1855–1859. ACM. find
  45. Linan Yue, Qi Liu, Lili Zhao, Li Wang, Weibo Gao, and Yanqing An. 2024. Event grounded criminal court view generation with cooperative (large) language models. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2024, Washington DC, USA, July 14-18, 2024, pages 2221–2230. ACM. find
  46. Han Zhang, Zhicheng Dou, Yutao Zhu, and Ji-Rong Wen. 2023. Contrastive learning for legal judgment prediction. ACM Trans. Inf. Syst., 41(4):113:1– 113:25. ↗
  47. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020a. Bertscore: Evaluating text generation with BERT. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. ↗
  48. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020b. Bertscore: Evaluating text generation with BERT. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. ↗
  49. Jie Zhao, Ziyu Guan, Cai Xu, Wei Zhao, and Enze Chen. 2022. Charge prediction by constitutive elements matching of crimes. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022, pages 4517–4523. ijcai.org. find
  50. Haoxi Zhong, Chaojun Xiao, Cunchao Tu, Tianyang Zhang, Zhiyuan Liu, and Maosong Sun. 2020. JEC-QA: A legal-domain question answering dataset. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pages 9701–9708. AAAI Press. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/shi-2026-legalchainreasoner-grounding-criminal-judicial-opinion/