New dataset and fine-tuned Llama model tackle U.S. immigration law

Researchers have developed ImmigrationQA, a new dataset containing over 17,000 question-answer pairs focused on U.S. immigration law, sourced from official documents and community forums. They fine-tuned a Llama 3.2 3B Instruct model using parameter-efficient LoRA on this dataset, achieving a 27% improvement in mean score compared to the base model. While the fine-tuned model shows gains in procedural areas, it still struggles with complex legal reasoning, and the project's artifacts are publicly released. AI

IMPACT Provides a specialized dataset and fine-tuned model to improve AI's understanding of complex legal domains.

RANK_REASON The cluster describes the creation of a new dataset and the fine-tuning of a model for a specific domain, which is a research milestone. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• BIA precedent decisions
• Claude Sonnet
• Claude Sonnet 4.6
• ImmigrationQA
• Llama 3.2 3B Instruct
• Llama 3 8B
• LoRA
• USCIS Policy Manual

• paper
• product
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →