Package com.google.genai.types
Class ReinforcementTuningAutoraterScorerExactMatchScorer
java.lang.Object
com.google.genai.JsonSerializable
com.google.genai.types.ReinforcementTuningAutoraterScorerExactMatchScorer
Scores autorater responses by using exact string match reward scorer. This data type is not
supported in Gemini API.
-
Nested Class Summary
Nested ClassesModifier and TypeClassDescriptionstatic classBuilder for ReinforcementTuningAutoraterScorerExactMatchScorer. -
Field Summary
Fields inherited from class com.google.genai.JsonSerializable
MAX_READ_LENGTH_PROPERTY -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionbuilder()Instantiates a builder for ReinforcementTuningAutoraterScorerExactMatchScorer.Assigns this reward score if the parsed response string equals the expression.The string expression to match against for scoring.Deserializes a JSON string to a ReinforcementTuningAutoraterScorerExactMatchScorer object.Creates a builder with the same values as this instance.Assigns this reward score if the parsed reward value does not equal the expression.Methods inherited from class com.google.genai.JsonSerializable
fromJsonNode, fromJsonString, objectMapper, setMaxReadLength, stringToJsonNode, toJson, toJsonNode, toJsonString
-
Constructor Details
-
ReinforcementTuningAutoraterScorerExactMatchScorer
public ReinforcementTuningAutoraterScorerExactMatchScorer()
-
-
Method Details
-
correctAnswerReward
Assigns this reward score if the parsed response string equals the expression. -
wrongAnswerReward
Assigns this reward score if the parsed reward value does not equal the expression. -
expression
The string expression to match against for scoring. This field supports placeholders in the format of {{references.key}} that will be replaced before matching. Regex is not supported for this expression. For example, users can define an ExactMatchScorer as follows: { "correctAnswerReward": 1.0, "wrongAnswerReward": -1.0, "expression": "{{references.concise_answer}}" } When evaluating the reward for each parsed autorater response, if the prompt references in the training/validation dataset has the following fields: ``` { "example": ..., "references": { "concise_ansser": "Yes", "verbose_answer": "The answer is Yes" } } ``` The above ExactMatchScorer will be replaced as follows for scoring: ``` { "correctAnswerReward": 1.0, "wrongAnswerReward": -1.0, "expression": "Yes" } ``` If the *parsed* autorater response is equal to the string `"Yes"`, then the reward is `1.0`, otherwise the reward is `-1.0`. -
builder
Instantiates a builder for ReinforcementTuningAutoraterScorerExactMatchScorer. -
toBuilder
Creates a builder with the same values as this instance. -
fromJson
Deserializes a JSON string to a ReinforcementTuningAutoraterScorerExactMatchScorer object.
-