Skip to contents

Weighted helpful / harmless / honest rubric score; the default weights are 1/3 each.

Usage

morie_kamath_3h_alignment(
  helpful_score,
  harmless_score,
  honest_score,
  weights = NULL
)

Arguments

helpful_score, harmless_score, honest_score

Aligned score vectors.

weights

Optional three weights.

Value

List with estimate, score, weights.

Examples

morie_kamath_3h_alignment(helpful_score = c(1, 2, 3, 4, 5, 6, 7, 8),
  harmless_score = c(1, 2, 3, 4, 5, 6, 7, 8), honest_score = c(1, 2, 3, 4, 5, 6, 7, 8))
#> $estimate
#> [1] 1 2 3 4 5 6 7 8
#> 
#> $score
#> [1] 1 2 3 4 5 6 7 8
#> 
#> $weights
#> [1] 0.3333333 0.3333333 0.3333333
#> 
#> $weight_sum
#> [1] 1
#> 
#> $n
#> [1] 8
#> 
#> $method
#> [1] "3H alignment score (Kamath Ch 5)"
#>