Using {{model}}, score sentiment for {{text_samples}} on a 1-10 scale. Calibration examples: - "{{positive_example}}" → 9/10 (highly positive) - "{{neutral_example}}" → 5/10 (neutral) - "{{negative_example}}" → 2/10 (negative) Score remaining samples and compare to {{benchmark_scores}}.
82 copies0 forks
Details
Category
AnalysisUse Cases
Sentiment calibrationScoring alignmentAnalysis validation
Works Best With
claude-opus-4.5gpt-5.2gemini-2.0-flash
Created Shared