Classify text against a taxonomy — classify

Assigns one taxonomy level to each element of x. The general form; for course and session objectives use classify_objectives(), which builds the ids that check_level_consistency() joins on.

Usage

classify_levels(
  x,
  llmconfig,
  taxonomy = "blooms_revised",
  ids = NULL,
  kind = "learning outcome",
  course_id = "course",
  repeats = 1L,
  rationale = TRUE,
  verbosity = 1L,
  ...
)

Arguments

x: Character: Texts to classify.
llmconfig: rtemis.llm::LLMConfig: Model configuration.
taxonomy: Character or Taxonomy: Classification scheme. See list_taxonomies().
ids: Character: Identifier per element of x. Defaults to <course_id>.ITEM.nn. Supply ids that match a Mapping's from_id and to_id if the result is to be checked against one.
kind: Character: What the texts are, as a noun phrase used in the prompt and recorded per item, e.g. "course objective".
course_id: Character: Course identifier, recorded on every row.
repeats: Integer [1, Inf): Independent raters per item. Bloom coding disagrees between human raters at the adjacent-level boundary, so a single rater's level is a point estimate with no visible spread; repeats > 1 fills confidence and keeps every rating in ratings.
rationale: Logical: Whether to ask for a one-sentence justification.
verbosity: Integer [0, Inf): Verbosity level.
...: Additional per-call arguments forwarded to rtemis.llm::generate(), e.g. temperature, seed.

Value

Classification object.

Author

EDG

Examples

if (FALSE) { # \dontrun{
  classify_levels(
    c("Describe the bias-variance tradeoff.", "Design a validation scheme."),
    llmconfig = config_Ollama("granite4.2:8b", temperature = 0),
    kind = "course objective"
  )
} # }