AfroBench: How Good are Large Language Models on African Languages? (#2825)

* add afrixnli to task

* add chat completion

* remove chat completion -untested

* afrimmlu added

* afrimmlu folder update

* afrimmlu folder update

* updated prompt

* remove print

* add afrimgsm -direct

* add squad metric

* fix bash script

* remove direct util, update common yaml

* remove print

* add few show. metric fixes

* fix direct path, add bash script for gpt models

* added transate test

* update afrixnli tasks

* update afrixnli tasks

* update metrics for afrixnli

* prompt translations fix

* prompt translations fix

* filter and metric fix -mgsm

* remove squad metric

* remove squad metric

* add f1 score to mgsm

* add f1 score to mgsm

* update native-direct with lin

* change f1 function

* add lin to utils

* add utils

* remove test limit

* remove test configs

* add swahili to mmlu

* change eng to ewe in ewe yaml mmlu

* add squad metric to mgsm, remove whitespace filter

* added translate test

* added afrixnli_translate

* fix exact match valueError

* fix exact match valueError

* restructure mmlu folder

* spacing

* remove afrimmlu_translate folder

* add utility

* format task name, clean ups

* modefied mgsm

* update on afrimgsm

* update on afrimgsm

* removed utils

* other mgsm varieties

* other mgsm varieties

* adding trasnslate direct

* Update translate_direct_yaml

* add manual xnli prompt, add multichoice for openai models, and adapt multichoice metric for openai model

* edit for open models

* Update translate_direct_yaml

* add verbalizer for xnli

* change xnli from multiple choice to generate

* add manual accuracy scores

* revert xnli to multiple choice

* change afrimgsm utils

* revert xnli to multiple_choice

* cleanups and readmes

* remove openai fixes and unused regex

* pr review changes

* revert metrics.py, task.py and extraction.py to main version

* add afrisenti

* utilities

* pulled from main

* add afrixnli

* add afrimmlu

* update afrixnli prompts

* mising senti language

* fix afrisenti prompt 2

* fix afrisenti prompts

* fix afrisenti prompts

* configure task grouping

* add multiple prompts to afrixnli for irokobench

* add multiple prompts to afrimmlu for irokobench

* Update afrixnli_yaml

* fixes and moves

* fixes and moves

* afrimmlu multiple prompts configs

* remove validation set from afrimmlu

* remove eng from afrimmlu translate test

* correct dataset path

* multiple prompts for mgsm

* file restructure

* afribench grouping

* repo restructuring

* repo restructuring

* update exact match to hugging face exact match and add new mgsm language

* remove decontamination

* update generation kwargs

* update generation kwargs for all mgsm prompts

* remove lang

* update generation kwargs for afrimgsm translatetest

* add afrimgsm cot for direct and translate

* remove eng from translate-cot

* add masakhaPOS tasks

* remove changes from task script

* add masakhanews tasks

* add uhura arc easy

* add afriqa and belebele files

* add tags for easier run. add naija rc

* add new metrics and transformation scripts

* fix afriqa swa fewshot split

* add naijarc

* add afrobench lite tasks

* update afrobench

* update afrobench

* remove unverified files to avoid bugs

* remove files not needed

* add afrobench tasks

* add afrobench tasks

* change to version 1

* change to version 1

* update afrobench

* update afrobench

* restore metric to original script

* update readme instructions

* add individual dataset readmes

* add link to collections

* correct run script

* align with main

* align with main

* align with main

* align with main

* align with main

* align with main

* align with main

* align with main

* failed run fixes

* failed run fixes

* add afrimgsm cot

* Apply precommit fixes

* update mafand dataset name

* pull request fixes

* remove afrihate due to availability

---------
Co-authored-by: Israel Abebe Azime <azime@cg.uni-saarland.de>
Co-authored-by: Israel Abebe Azime <se.israel.abebe@gmail.com>
Co-authored-by: David Adelani <davlanade@gmail.com>
Co-authored-by: theyorubayesian <akin.o.oladipo@gmail.com>

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+doc_to_text: "For mathematical questions provided in Sesotho language. Supply the\
+  \ accurate step by step answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nStep by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_sot_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+doc_to_text: "For mathematical questions provided in Swahili language. Supply the\
+  \ accurate step by step answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nStep by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_swa_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+doc_to_text: "For mathematical questions provided in Twi language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_twi_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_vai.yaml

+# Generated by utils.py
+dataset_name: vai
+doc_to_text: "For mathematical questions provided in Vai language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_vai_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+doc_to_text: "For mathematical questions provided in Wolof language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_wol_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+doc_to_text: "For mathematical questions provided in isiXhosa language. Supply the\
+  \ accurate step by step answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nStep by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_xho_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_yaml

+tag: afrimgsm_tt_cot_tasks
+dataset_path: masakhane/afrimgsm-translate-test
+dataset_name: null  # Overridden by language-specific config.
+output_type: generate_until
+test_split: test
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "The answer is (\\-?[0-9\\.\\,]+)"
+      - function: "take_first"
+  - filter:
+    - function: regex
+      group_select: -1
+      regex_pattern: (-?[$0-9.,]{2,})|(-?[0-9]+)
+    - function: take_first
+    name: flexible-extract
+metadata:
+  version: 2.0

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+doc_to_text: "For mathematical questions provided in Yoruba language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_yor_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+doc_to_text: "For mathematical questions provided in Zulu language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_zul_prompt_5

lm_eval/tasks/afrimmlu/direct/afrimmlu.yaml

+group: afrimmlu-irokobench
+task:
+  - afrimmlu_tasks_prompt_1
+  - afrimmlu_tasks_prompt_2
+  - afrimmlu_tasks_prompt_3
+  - afrimmlu_tasks_prompt_4
+  - afrimmlu_tasks_prompt_5
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 2

lm_eval/tasks/afrimmlu/direct/afrimmlu_common_yaml

-tag:
-  - afrimmlu
-  - afrimmlu_direct
-task: null
-dataset_path: masakhane/afrimmlu
-dataset_name: null
-output_type: multiple_choice
-validation_split: validation
-test_split: test
-fewshot_split: validation
-doc_to_text: !function utils.doc_to_text
-doc_to_target: "{{['A', 'B', 'C', 'D'].index(answer)}}"
-doc_to_choice: !function utils.doc_to_choice
-should_decontaminate: true
-doc_to_decontamination_query: "Question: {{question}}\nAnswer:"
-metric_list:
-  - metric: f1
-    aggregation: !function utils.weighted_f1_score
-    # aggregation: mean
-    average: weighted
-    hf_evaluate: true
-    higher_is_better: True
-    ignore_case: true
-    ignore_punctuation: true
-    regexes_to_ignore:
-      - ","
-      - "\\$"
-  - metric: acc
-    aggregation: mean
-    higher_is_better: true
-    ignore_case: true
-    ignore_punctuation: true
-    regexes_to_ignore:
-      - ","
-      - "\\$"
-metadata:
-  version: 1.0

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_amh.yaml

-dataset_name: amh
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_amh

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_eng.yaml

-dataset_name: eng
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_eng

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_ewe.yaml

-dataset_name: ewe
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_ewe

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_fra.yaml

-dataset_name: fra
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_fra

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_hau.yaml

-dataset_name: hau
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_hau

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_ibo.yaml

-dataset_name: ibo
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_ibo

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_kin.yaml

-dataset_name: kin
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_kin

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_lin.yaml

-dataset_name: lin
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_lin

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_lug.yaml

-dataset_name: lug
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_lug