# Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDastaavej

Source: [Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDastaavej](<https://www.sota2.com/research/paper/68fa77c41e209131cea75331>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-27T05:00:04.193Z

Authors: Shubham Kumar Nigam, Balaramamahanthi Deepak Patnaik, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya

Published: 2025-04-04T14:41:50.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Legal Document Generation on Legal Document Drafting Dataset (test)](<https://www.sota2.com/research/sota/legal-document-generation-on-legal-document-drafting-dataset-test.md>): Legal Document Generation; Legal Document Drafting Dataset (test); RL Score: 0.15.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.03486>)

[PDF](<https://arxiv.org/pdf/2504.03486.pdf>)
