Fix Column Naming and Dataset Naming Conventions in K-MMLU Evaluation (#1171)

* Correct column names and dataset names

* Remove kmmlu_general_physics.yaml and kmmlu_korean_language.yaml

* Update _default_kmmlu_yaml

---------
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

lm_eval/tasks/kmmlu/kmmlu_materials_engineering.yaml

-"dataset_name": "Materials Engineering"
+"dataset_name": "Materials-Engineering"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_materials_engineering"

lm_eval/tasks/kmmlu/kmmlu_mechanical_engineering.yaml

-"dataset_name": "Mechanical Engineering"
+"dataset_name": "Mechanical-Engineering"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_mechanical_engineering"

lm_eval/tasks/kmmlu/kmmlu_nondestructive_testing.yaml

-"dataset_name": "Nondestructive Testing"
+"dataset_name": "Nondestructive-Testing"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_nondestructive_testing"

lm_eval/tasks/kmmlu/kmmlu_political_science_and_sociology.yaml

-"dataset_name": "Political Science and Sociology"
+"dataset_name": "Political-Science-and-Sociology"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_political_science_and_sociology"

lm_eval/tasks/kmmlu/kmmlu_public_safety.yaml

-"dataset_name": "Public Safety"
+"dataset_name": "Public-Safety"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_public_safety"

lm_eval/tasks/kmmlu/kmmlu_railway_and_automotive_engineering.yaml

-"dataset_name": "Railway and Automotive Engineering"
+"dataset_name": "Railway-and-Automotive-Engineering"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_railway_and_automotive_engineering"

lm_eval/tasks/kmmlu/kmmlu_real_estate.yaml

-"dataset_name": "Real Estate"
+"dataset_name": "Real-Estate"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_real_estate"

lm_eval/tasks/kmmlu/kmmlu_refrigerating_machinery.yaml

-"dataset_name": "Refrigerating Machinery"
+"dataset_name": "Refrigerating-Machinery"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_refrigerating_machinery"

lm_eval/tasks/kmmlu/kmmlu_social_welfare.yaml

-"dataset_name": "Social Welfare"
+"dataset_name": "Social-Welfare"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_social_welfare"

lm_eval/tasks/kmmlu/kmmlu_telecommunications_and_wireless_technology.yaml

-"dataset_name": "Telecommunications and Wireless Technology"
+"dataset_name": "Telecommunications-and-Wireless-Technology"
 "include": "_default_kmmlu_yaml"
 "task": "kmmlu_telecommunications_and_wireless_technology"

lm_eval/tasks/kmmlu/utils.py

@@ -7,7 +7,7 @@ def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:
             f"다음을 읽고 정답으로 알맞은 것을 고르시요.\n"
             f"### Question: {doc['question']}\n"
             f"### Options:\n"
-            f"(1) {doc['option#1']}\n(2) {doc['option#2']}\n(3) {doc['option#3']}\n(4) {doc['option#4']}\n"
+            f"(1) {doc['A']}\n(2) {doc['B']}\n(3) {doc['C']}\n(4) {doc['D']}\n"
             f"### Answer: 주어진 문제의 정답은"
         )
         out_doc = {