构建印度私法文书生成新数据集与通用框架，提升法律文书自动化质量。
Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDastaavej
- 用两阶段框架先规划结构再生成内容，适配各类大模型。
- 在133类法律文书上验证，生成结果准确率和连贯性显著优于基线。
- 适合法律AI研究者、法律科技开发者及司法数字化推进者。
自动化法律文书起草可提升效率并减轻人工负担。然而，由于公开数据集稀缺且长文本法律起草模型适配复杂，私有法律文书的结构化生成仍鲜有人关注，尤其在印度语境下。为此，我们提出VidhikDastaavej——一个与印度律师事务所合作构建的大规模匿名私法文书数据集，涵盖133类文书，是该领域首个同类资源，为结构化法律文本生成与法律AI研究奠定基础。我们进一步提出模型无关封装器（MAW），一种两阶段生成框架：首先规划文书结构，再通过检索增强提示生成各部分。该方法不依赖特定大语言模型，可在开源与闭源模型间灵活迁移。综合评估包括词汇、语义、大模型判别及专家评审，并计算标注者间一致性，结果显示该框架在事实准确性、连贯性和完整性方面显著优于微调基线。本工作确立了新的基准数据集与可复用的生成框架，推动未来法律辅助起草的AI研究发展。
原文摘要 · Abstract (English)
Automating legal document drafting can improve efficiency and reduce the burden of manual legal work. Yet, the structured generation of private legal documents remains underexplored, particularly in the Indian context, due to the scarcity of public datasets and the complexity of adapting models for long-form legal drafting. To address this gap, we introduce VidhikDastaavej, a large-scale, anonymized dataset of private legal documents curated in collaboration with an Indian law firm. Covering 133 diverse categories, this dataset is the first resource of its kind and provides a foundation for research in structured legal text generation and Legal AI more broadly. We further propose a Model-Agnostic Wrapper (MAW), a two-stage generation framework that first plans the section structure of a legal draft and then generates each section with retrieval-based prompts. MAW is independent of any specific LLM, making it adaptable across both open- and closed-source models. Comprehensive evaluation, including lexical, semantic, LLM-based, and expert-driven assessments with inter-annotator agreement, shows that the wrapper substantially improves factual accuracy, coherence, and completeness compared to fine-tuned baselines. This work establishes both a new benchmark dataset and a generalizable generation framework, paving the way for future research in AI-assisted legal drafting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。