Metraipolis › archive › dc_ded1d8911363

JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction — arXiv:2608.29616

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.29616
License (as archived): CC0-1.0
Archived: 2026-10-17T08:07:05.677Z
SHA-256 of the archived text: b00eb7b18f5120affa0d73b4f00e459270be0ea969497acb3d8aee4775f62897
Stable URL of this page: https://metraipolis.com/documento/dc_ded1d8911363

How to cite

JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction — arXiv:2608.29616 — arXiv (en), https://arxiv.org/abs/2608.29616 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ded1d8911363 (Metraipolis archive dc_ded1d8911363, sha256 b00eb7b18f5120affa0d73b4f00e459270be0ea969497acb3d8aee4775f62897)

BibTeX

@misc{dcded1d8911363,
  title = {JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction — arXiv:2608.29616},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29616},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ded1d8911363; sha256 b00eb7b18f5120affa0d73b4f00e459270be0ea969497acb3d8aee4775f62897},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29616. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Criminal judgment prediction requires models to infer statutory articles, charges, and sentencing outcomes from case facts. Unlike standard classification tasks, it involves a structured reasoning process in which statutes should be matched with facts, charges should be justified by statutes, and sentencing outcomes should remain consistent with charges. Existing approaches optimize final labels, and while some have attempted to evaluate reasoning quality, their evaluations are indirect, often relying on LLM-generated rubrics that reflect model-internal preferences rather than the inherent logical structure of legal adjudication. We propose Juris Policy Optimization (JPO), a post-training framework for structured legal reasoning in Chinese criminal judgment prediction. JPO first uses teacher-generated rationales to supervise a standardized four-step reasoning process, and then applies reinforcement learning with a composite reward over legal prediction quality, reasoning structure completeness, and cross-step consistency. JPO further introduces token-level advantage reweighting and adaptive clipping for legally salient reasoning segments. Experiments on multiple open-source language models and three Chinese legal benchmarks show that JPO consistently improves both judgment prediction and reasoning quality over supervised fine-tuning and reinforcement learning baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.29616 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:47:52.722Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).