Medical LLM safety demonstrations, splits, and harmfulness prompts. The dataset appears designed for evaluating the safety of large language models in medical contexts. Details on its size, creator, and update frequency are not provided in the input.
Use Cases
- Benchmarking medical LLM safety based on provided demonstrations and prompts.
- Training safety classifiers or filters using the harmfulness prompts.
- Analyzing failure modes of LLMs in medical conversations based on the described splits.
Strengths
- Focuses on a critical niche for AI deployment: medical LLM safety.
- Includes structured components like demonstrations and splits, suggesting a benchmark format.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Row count is unknown, which may limit suitability assessment.
- Column-level documentation is absent; field semantics must be inferred after download.