Study 2 Results: Participant Perceptions of LLM-Generated Psychosocial Risk Responses

A dataset from figshare authored by Laura M. Vowels, last updated on 2026-04 27. It contains results from Study 2, which examined participants' perceptions of large language model (LLM)-generated responses for psychosocial risk assessment. The 9.5 KB Excel file likely contains ratings on accuracy, empathy, and clinical usefulness across risk domains like suicide, intimate partner violence, and substance misuse.

Use Cases

• Analyze participant-rated perceptions of LLM empathy and accuracy based on the described study design.
• Compare human judgments of clinical usefulness across different psychosocial risk domains mentioned in the description.
• Benchmark user acceptance metrics for conversational AI agents in mental health screening.

Strengths

• Data is openly licensed under CC-BY-4.0.
• File size is 9.5 KB, indicating a compact and focused dataset.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

figshare

Collection Method

Likely collected via a research study evaluating participant perceptions of LLM outputs.

Time Range

null

Freshness

Last updated 2026-04-27 17:45:16; freshness should be verified.

Geography

null