Skip to main content

Medicine

AutoElicit (ICL baseline)

GPT-3.5-turbo in-context-learning baseline from AutoElicit: direct per-instance classification of tabular clinical/quality datasets (breast cancer, heart disease, hypothyroid, wine quality). Response is correctness of the 0.5-thresholded LLM probability.

425items
1subjects
100%observed
MITlicense
medicinedomain
reasoningdomain
textmodality

Response matrix

Fit to width. Hover for subject & item; click a cell for details.

AutoElicit (ICL baseline) response matrix: AI models (rows) against items (columns)
Correct (1)Incorrect (0)Unobserved

Scale: 1 = correct · 0 = incorrect

Subjects

  1. 1gpt-3.5-turbo-01250.5029