Likert Scale
A common psychometric instrument that asks raters to indicate their degree of agreement with a statement along an ordered scale. It is widely used in questionnaire research.
Timeline (last 90 days)
Existing mental health AI benchmarks typically have a large model simulate a patient in multi-turn dialogue and then use another LLM as a judge to score, but the simulated patients are often overly cooperative and overly self-analytical, and the evaluation criteria often rely on opaque Likert scales.
When different raters understand the same level very differently, the Likert scale leads to unstable inter-rater reliability, and a single number cannot carry information about specific good and bad dimensions.
All Facts (2)
Existing mental health AI benchmarks typically have a large model simulate a patient in multi-turn dialogue and then use another LLM as a judge to score, but the simulated patients are often overly cooperative and overly self-analytical, and the evaluation criteria often rely on opaque Likert scales.
50%UnverifiedWhen different raters understand the same level very differently, the Likert scale leads to unstable inter-rater reliability, and a single number cannot carry information about specific good and bad dimensions.
50%