Update evaluator_module.py (#3)

- Update evaluator_module.py (2095467f32da5e3c757a125109d48dda924c111c)


Co-authored-by: Manay Porwal <manayporwal07@users.noreply.huggingface.co>

evaluator_module.py

@@ -47,10 +47,10 @@ class AetherScoreEvaluator:
         query = (
             f"Prompt: {prompt}\n"
             f"Response: {response}\n\n"
-            "Evaluate the response and provide:\n"
-            "hallucination_score: float between 0 and 1 (1 = fully grounded, 0 = full hallucination)\n"
-            "assumption_control: float between 0 and 1 (1 = no assumptions, 0 = many unsupported assumptions)\n"
-            "Then explain briefly in one or two sentences."
+            "First, output ONLY two scores on separate lines:\n"
+            "hallucination_score=<float between 0 and 1>\n"
+            "assumption_control=<float between 0 and 1>\n"
+            "Then, after that, give a short explanation (1–2 sentences)."
         )
 
         # Calling our LLM
@@ -68,13 +68,13 @@ class AetherScoreEvaluator:
         assumption_score = 0.0
         explanation = output
 
-        match_h = re.search(r"hallucination[_ ]?score[: ]?([01](?:\.\d+)?)", output, re.I)
-        match_a = re.search(r"assumption[_ ]?control[: ]?([01](?:\.\d+)?)", output, re.I)
-
+        match_h = re.search(r"hallucination[_ ]?(score)?[:= ]?\s*([0-1](?:\.\d+)?)", output, re.I)
+        match_a = re.search(r"assumption[_ ]?(control|score)?[:= ]?\s*([0-1](?:\.\d+)?)", output, re.I)
+        
         if match_h:
-            halluc_score = float(match_h.group(1))
+            halluc_score = float(match_h.group(2))
         if match_a:
-            assumption_score = float(match_a.group(1))
+            assumption_score = float(match_a.group(2))
 
         return {
             "hallucination_score": (halluc_score, explanation),