Soroosh Tayebi Arasteh
2 papers · Latest:
Natural Language Processing
Safety and accuracy follow different scaling laws in clinical large language models
Clinical LLM safety is not a passive consequence of scaling but a deployment property shaped by evidence quality, retrieval, and context.
2605.04039
Natural Language ProcessingCase-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision
Introduces Case-Grounded Evidence Verification, a framework with a novel supervision method to train models that genuinely depend on evidence for claims.
2604.09537
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.