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

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


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.
Anthology ID:
2026.lrec-1.530
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
6661–6673
Language:
External URL:
https://lrec.elra.info/lrec2026-main-530
DOI:
10.63317/2wswvwyqxt4k
Bibkey:
Cite (ACL):
Shubham Kumar Nigam, Deepak Patnaik Balaramamahanthi, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya. 2026. Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDastaavej. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 6661–6673, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDastaavej (Nigam et al., LREC 2026)
Copy Citation: