Aim 
The goal is to build a dementia-focused biomedical QA assistant that retrieves evidence from PubMed and PMC, generates answers with inline PMID citations, and ensures reliability by minimizing hallucinations through claim-level verification and selective abstention. The system emphasizes accessibility by relying on open and consumer-friendly tools, while its evaluation framework focuses on trustworthiness using metrics such as Attribution@k, Refusal Accuracy, and Claim-level Hallucination. In addition, a continued pretraining (CPT) component on biomedical and dementia literature is included to improve domain alignment, meet research requirements, and enhance publishability. 

Ask me for more information. Paper under submission.