CYAICLJan 30, 2024

Aalap: AI Assistant for Legal & Paralegal Functions in India

arXiv:2402.01758v19 citationsh-index: 4
Originality Synthesis-oriented
AI Analysis

This work addresses data privacy and domain-specific needs for legal professionals in India, though it is incremental as it builds on existing models with fine-tuning.

The authors tackled the challenge of applying large language models to legal tasks in India by fine-tuning Mistral 7B on domain-specific instructions, resulting in Aalap outperforming GPT-3.5-turbo in 31% of test data and matching it in 34% as evaluated by GPT-4.

Using proprietary Large Language Models on legal tasks poses challenges due to data privacy issues, domain data heterogeneity, domain knowledge sophistication, and domain objectives uniqueness. We created Aalalp, a fine-tuned Mistral 7B model on instructions data related to specific Indian legal tasks. The performance of Aalap is better than gpt-3.5-turbo in 31\% of our test data and obtains an equivalent score in 34\% of the test data as evaluated by GPT4. Training Aalap mainly focuses on teaching legal reasoning rather than legal recall. Aalap is definitely helpful for the day-to-day activities of lawyers, judges, or anyone working in legal systems.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes