AI RESEARCH
Towards end-to-end LLM-based censoring-aware survival analysis
arXiv CS.AI
•
ArXi:2605.25399v1 Announce Type: new Objective: Survival analysis is central to medical prediction, yet large language models (LLMs) are rarely used as end-to-end survival models because censoring prevents straightforward supervised fine-tuning. Here we present LLMSurvival, a framework that enables censoring-aware survival analysis with unmodified LLMs operating directly on tabular clinical data.