update

src/backend/envs.py

@@ -58,7 +58,6 @@ class Tasks(Enum):
     task20 = Task("race", "acc", "RACE", 0)
 
 
-
 EVAL_REQUESTS_PATH_BACKEND = os.path.join(CACHE_PATH, "eval-queue-bk")
 EVAL_RESULTS_PATH_BACKEND = os.path.join(CACHE_PATH, "eval-results-bk")
 

src/leaderboard/read_evals.py

@@ -93,7 +93,7 @@ class EvalResult:
 
                 if to_add is True:
                     multiplier = 100.0
-                    if 'rouge' in metric:
+                    if 'rouge' in metric and 'truthful' not in benchmark:
                         multiplier = 1.0
                     if 'squad' in benchmark:
                         multiplier = 1.0