Merge pull request #408 from aitomatic/examples/FinanceBench

update examples/FinanceBench labels

Author: TheVinhLuong102

examples/FinanceBench/ground-truths.yml

@@ -4288,6 +4288,8 @@ financebench_id_00603:
   correctness: >-
     the answer mentions new stores
 
+  evaluator-unreliable: true
+
 
 financebench_id_00605:
   sector: Consumer Discretionary
@@ -4316,6 +4318,8 @@ financebench_id_00605:
     the answer contains a calculated percentage value that is in the range from 30% to 40%
     (if the answer is a single number, assume that it is that calculated percentage value)
 
+  evaluator-unreliable: true
+
 
 financebench_id_00606:  # tricky: highly implicit wordings
   sector: Consumer Discretionary