AI RESEARCH
ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law
arXiv CS.AI
•
ArXi:2605.30589v1 Announce Type: cross U. S. immigration law spans thousands of pages of official policy, federal regulations, and procedural guidance that change frequently and carry high stakes for petitioners who lack legal representation. We describe the construction of ImmigrationQA, a source-grounded question-answering dataset of 17,058 pairs across 13 immigration subdomains, and the fine-tuning of a Llama 3.2 3B Instruct model on that dataset using parameter-efficient LoRA.