fix: rubrics based metrics (#1821)

- #1800

---------

Co-authored-by: ikka <[email protected]>

docs/concepts/metrics/available_metrics/general_purpose.md

@@ -69,28 +69,38 @@ await scorer.single_turn_ascore(sample)
 
 ## Rubrics based criteria scoring
 
-Domain specific evaluation metric is a rubric-based evaluation metric that is used to evaluate responses on a specific domain. The rubric consists of descriptions for each score, typically ranging from 1 to 5. The response here is evaluation and scored using the LLM using description specified in the rubric. This metric also have reference free and reference based variations.
+The Rubric-Based Criteria Scoring Metric is used to do evaluations based on user-defined rubrics. Each rubric defines a detailed score description, typically ranging from 1 to 5. The LLM assesses and scores responses according to these descriptions, ensuring a consistent and objective evaluation. 
+!!! note
+    When defining rubrics, ensure consistency in terminology to match the schema used in the `SingleTurnSample` or `MultiTurnSample` respectively. For instance, if the schema specifies a term such as reference, ensure that the rubrics use the same term instead of alternatives like ground truth.
 
 #### Example
 ```python
 from ragas.dataset_schema import SingleTurnSample
 from ragas.metrics import RubricsScore
+
 sample = SingleTurnSample(
-    user_input="Where is the Eiffel Tower located?",
-    response="The Eiffel Tower is located in Paris.",
-    reference="The Eiffel Tower is located in Paris.",
+    response="The Earth is flat and does not orbit the Sun.",
+    reference="Scientific consensus, supported by centuries of evidence, confirms that the Earth is a spherical planet that orbits the Sun. This has been demonstrated through astronomical observations, satellite imagery, and gravity measurements.",
 )
+
 rubrics = {
-    "score1_description": "The response is incorrect, irrelevant, or does not align with the ground truth.",
-    "score2_description": "The response partially matches the ground truth but includes significant errors, omissions, or irrelevant information.",
-    "score3_description": "The response generally aligns with the ground truth but may lack detail, clarity, or have minor inaccuracies.",
-    "score4_description": "The response is mostly accurate and aligns well with the ground truth, with only minor issues or missing details.",
-    "score5_description": "The response is fully accurate, aligns completely with the ground truth, and is clear and detailed.",
+    "score1_description": "The response is entirely incorrect and fails to address any aspect of the reference.",
+    "score2_description": "The response contains partial accuracy but includes major errors or significant omissions that affect its relevance to the reference.",
+    "score3_description": "The response is mostly accurate but lacks clarity, thoroughness, or minor details needed to fully address the reference.",
+    "score4_description": "The response is accurate and clear, with only minor omissions or slight inaccuracies in addressing the reference.",
+    "score5_description": "The response is completely accurate, clear, and thoroughly addresses the reference without any errors or omissions.",
 }
-scorer =  RubricsScore(rubrics=rubrics, llm=evaluator_llm)
+
+
+scorer = RubricsScore(rubrics=rubrics, llm=evaluator_llm)
 await scorer.single_turn_ascore(sample)
 ```
 
+Output
+```
+1
+```
+
 ## Instance Specific rubrics criteria scoring
 
 Instance specific evaluation metric is a rubric-based evaluation metric that is used to evaluate responses on a specific instance, ie each instance to be evaluated is annotated with a rubric based evaluation criteria. The rubric consists of descriptions for each score, typically ranging from 1 to 5. The response here is evaluation and scored using the LLM using description specified in the rubric. This metric also have reference free and reference based variations. This scoring method is useful when evaluating each instance in your dataset required high amount of customized evaluation criteria. 

src/ragas/metrics/_domain_specific_rubrics.py

@@ -24,19 +24,19 @@
 
 
 DEFAULT_REFERENCE_FREE_RUBRICS = {
-    "score1_description": "The response is incorrect or does not answer the question.",
-    "score2_description": "The response is partially correct but may include errors or incomplete information.",
-    "score3_description": "The response is generally correct but lacks clarity or completeness.",
-    "score4_description": "The response is correct and clear, with minor issues or missing details.",
-    "score5_description": "The response is completely accurate, clear, and answers the question directly.",
+    "score1_description": "The response is entirely incorrect and fails to address any aspect of the user input.",
+    "score2_description": "The response contains partial accuracy but includes major errors or significant omissions that affect its relevance to the user input.",
+    "score3_description": "The response is mostly accurate but lacks clarity, thoroughness, or minor details needed to fully address the user input.",
+    "score4_description": "The response is accurate and clear, with only minor omissions or slight inaccuracies in addressing the user input.",
+    "score5_description": "The response is completely accurate, clear, and thoroughly addresses the user input without any errors or omissions.",
 }
 
 DEFAULT_WITH_REFERENCE_RUBRICS = {
-    "score1_description": "The response is incorrect, irrelevant, or does not align with the ground truth.",
-    "score2_description": "The response partially matches the ground truth but includes significant errors, omissions, or irrelevant information.",
-    "score3_description": "The response generally aligns with the ground truth but may lack detail, clarity, or have minor inaccuracies.",
-    "score4_description": "The response is mostly accurate and aligns well with the ground truth, with only minor issues or missing details.",
-    "score5_description": "The response is fully accurate, aligns completely with the ground truth, and is clear and detailed.",
+    "score1_description": "The response is entirely incorrect, irrelevant, or does not align with the reference in any meaningful way.",
+    "score2_description": "The response partially matches the reference but contains major errors, significant omissions, or irrelevant information.",
+    "score3_description": "The response aligns with the reference overall but lacks sufficient detail, clarity, or contains minor inaccuracies.",
+    "score4_description": "The response is mostly accurate, aligns closely with the reference, and contains only minor issues or omissions.",
+    "score5_description": "The response is fully accurate, completely aligns with the reference, and is clear, thorough, and detailed.",
 }
 
 
@@ -71,13 +71,13 @@ class MultiTurnInputWithoutRubric(BaseModel):
 
 
 class SingleTurnPrompt(PydanticPrompt[SingleTurnInputWithoutRubric, ScoreFeedback]):
-    instruction = ""  # this will be set in the constructor
+    instruction = "Your task is to assign an appropriate score and provide feedback to the inputs based solely on the scoring criteria."
     input_model = SingleTurnInputWithoutRubric
     output_model = ScoreFeedback
 
 
 class MultiTurnPrompt(PydanticPrompt[MultiTurnInputWithoutRubric, ScoreFeedback]):
-    instruction = ""  # this will be set in the constructor
+    instruction = "Your task is to assign an appropriate score and provide feedback to the inputs based solely on the scoring criteria."
     input_model = MultiTurnInputWithoutRubric
     output_model = ScoreFeedback
 
@@ -111,6 +111,12 @@ def __init__(
                 "reference:optional",
             },
         }
+
+        # Add rubrics to the scoring prompts
+        rubrics_text = "\n".join(f"{key}: {value}" for key, value in self.rubrics.items())
+        self.single_turn_scoring_prompt.instruction = f"{self.single_turn_scoring_prompt.instruction}\n\nScoring Rubrics:\n{rubrics_text}\n"
+        self.multi_turn_scoring_prompt.instruction = f"{self.multi_turn_scoring_prompt.instruction}\n\nScoring Rubrics:\n{rubrics_text}\n"
+
         super().__init__(
             name=name,
             llm=llm,
@@ -142,6 +148,7 @@ async def _ascore(self, row: t.Dict, callbacks: Callbacks) -> float:
             reference=reference,
             reference_contexts=reference_contexts,
         )
+
         output = await self.single_turn_scoring_prompt.generate(
             data=prompt_input,
             llm=self.llm,
@@ -158,6 +165,7 @@ async def _multi_turn_ascore(
         prompt_input = MultiTurnInputWithoutRubric(
             user_input=interaction,
         )
+
         output = await self.multi_turn_scoring_prompt.generate(
             data=prompt_input,
             llm=self.llm,