ReinforcementTuningAutoraterScorer

@Serializable
data class ReinforcementTuningAutoraterScorer(val autoraterConfig: AutoraterConfig? = null, val autoraterPrompt: String? = null, val autoraterResponseParseConfig: ReinforcementTuningParseResponseConfig? = null, val parsedResponseConversionScorer: ReinforcementTuningAutoraterScorerParsedResponseConversionScorer? = null, val exactMatchScorer: ReinforcementTuningAutoraterScorerExactMatchScorer? = null)

Reinforcement tuning autorater scorer.

Constructors

Link copied to clipboard
constructor(autoraterConfig: AutoraterConfig? = null, autoraterPrompt: String? = null, autoraterResponseParseConfig: ReinforcementTuningParseResponseConfig? = null, parsedResponseConversionScorer: ReinforcementTuningAutoraterScorerParsedResponseConversionScorer? = null, exactMatchScorer: ReinforcementTuningAutoraterScorerExactMatchScorer? = null)

Properties

Link copied to clipboard

Autorater config for evaluation.

Link copied to clipboard
val autoraterPrompt: String? = null

The prompt for an autorater to scorer the parsed sample response. This field supports the following placeholders that will be replaced before scoring: - {{prompt}} - {{response}} - {{system_instruction}} - {{references.key}}

Link copied to clipboard

Parses autorater returned response for scoring. For example, if the autorater response has reward stored in the 2.0 block, defining a parsing response config using regex ".*(.*?)" will return a score "2.0".

Link copied to clipboard

Scores autorater responses by using string match reward scorer.

Link copied to clipboard

Scores autorater responses by directly converting parsed autorater response to a float reward. Note: Reward is clipped to be within [-1, 1], i.e., reward = max(min(reward, 1.0), -1.0).