A large-scale, multimodal benchmark for assessing AI-driven medical dialogue systems. The dataset, created by univanxx and last updated on 2025-09-23, simulates realistic telemedicine consultations between a Doctor Agent and a temperament-driven Patient Agent using image and text inputs.
Use Cases
- Benchmarking AI-driven medical dialogue systems based on multimodal inputs
- Simulating telemedicine consultations based on image and text inputs
- Evaluating multi-agent interactions between simulated doctor and patient agents
Strengths
- Designed as a large-scale benchmark for comprehensive evaluation
- Simulates realistic telemedicine consultations with multiple agent roles
Limitations
- Column-level documentation is absent; field semantics must be inferred after download
- Row count is unknown, which may limit suitability assessment
Provenance
- Source
- huggingface
- Freshness
- Last updated 2025-09-23 06:58:57