in lmms_eval/tasks/mmmu/utils.py [0:0]
def parse_open_response(response):
"""
Parse the prediction from the generated response.
Return a list of predicted strings or numbers.
https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c3508794/eval/eval_utils.py#L122
"""
# content = content.strip("\n").strip(".").strip(" ")
def get_key_subresponses(response):
key_responses = []
response = response.strip().strip(".").lower()
sub_responses = re.split(r"\.\s(?=[A-Z])|\n", response)
indicators_of_keys = [
"could be ",
"so ",
"is ",
"thus ",
"therefore ",
"final ",
"answer ",
"result ",
]
key_responses = []
for index, resp in enumerate(sub_responses):
# if last one, accept it's an equation (the entire response can be just one sentence with equation)
if index == len(sub_responses) - 1:
indicators_of_keys.extend(["="])
shortest_key_response = None # the shortest response that may contain the answer (tail part of the response)
for indicator in indicators_of_keys:
if indicator in resp:
if not shortest_key_response:
shortest_key_response = resp.split(indicator)[-1].strip()
else:
if len(resp.split(indicator)[-1].strip()) < len(shortest_key_response):
shortest_key_response = resp.split(indicator)[-1].strip()
# key_responses.append(resp.split(indicator)[1].strip())
if shortest_key_response:
# and it's not trivial
if shortest_key_response.strip() not in [
":",
",",
".",
"!",
"?",
";",
":",
"'",
]:
key_responses.append(shortest_key_response)
if len(key_responses) == 0: # did not found any
return [response]
return key_responses
# pdb.set_trace()
key_responses = get_key_subresponses(response)
pred_list = key_responses.copy() # keep the original string response
for resp in key_responses:
pred_list.extend(extract_numbers(resp))
tmp_pred_list = []
for i in range(len(pred_list)):
tmp_pred_list.extend(normalize_str(pred_list[i]))
pred_list = tmp_pred_list
# remove duplicates
pred_list = list(set(pred_list))
return pred_list