How Good Are Patient-Facing LLMs at Survivorship Questions? A Comparative User Evaluation Across Four Chatbots

Cancer survivors increasingly consult chatbots between visits, but conditions for safe use remain unclear. The goal of this study was to characterize survivors' judgments of patient-facing LLM responses and derive deployment requirements. We conducted semi-structured interviews with 21 breast and prostate cancer survivors immediately after a structured rating task; transcripts were dual-coded and analyzed thematically. Three themes governed willingness to act: trust, accuracy, and provenance; personalization and empathy in the cancer context; and usability, actionability, and risk-based escalation. Survivors favored citation-first answers, lightweight personalization, plain-language steps, and one-tap clinician escalation. Patient-defined requirements aligned with European priorities, informing trustworthy, integrated survivorship deployments.