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/afrimmlu/direct/prompt_4/afrimmlu_direct_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+include: afrimmlu_direct
+task: afrimmlu_direct_sna_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+include: afrimmlu_direct
+task: afrimmlu_direct_sot_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+include: afrimmlu_direct
+task: afrimmlu_direct_swa_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+include: afrimmlu_direct
+task: afrimmlu_direct_twi_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+include: afrimmlu_direct
+task: afrimmlu_direct_wol_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrimmlu_direct
+task: afrimmlu_direct_xho_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+include: afrimmlu_direct
+task: afrimmlu_direct_yor_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrimmlu_direct
+task: afrimmlu_direct_zul_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/utils.py

+from lm_eval.utils import weighted_f1_score
+
+
+def doc_to_choice(doc):
+    choices = eval(doc["choices"])
+    return choices
+
+
+def doc_to_text(doc):
+    output = """Analyze each question critically and determine the most correct option based on your understanding of the subject matter
+
+Question: {question}
+Choices:
+        A: {choice1}
+        B: {choice2}
+        C: {choice3}
+        D: {choice4}
+Answer: """
+
+    choices = eval(doc["choices"])
+    text = output.format(
+        question=doc["question"],
+        choice1=choices[0],
+        choice2=choices[1],
+        choice3=choices[2],
+        choice4=choices[3],
+    )
+    return text

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct

+tag:
+    - afrimmlu_tasks
+    - afrimmlu_tasks_prompt_5
+    - afrobench_mmlu_tasks
+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/prompt_5/afrimmlu_direct_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrimmlu_direct
+task: afrimmlu_direct_amh_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_eng.yaml

+# Generated by utils.py
+dataset_name: eng
+include: afrimmlu_direct
+task: afrimmlu_direct_eng_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrimmlu_direct
+task: afrimmlu_direct_ewe_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrimmlu_direct
+task: afrimmlu_direct_fra_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrimmlu_direct
+task: afrimmlu_direct_hau_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrimmlu_direct
+task: afrimmlu_direct_ibo_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+include: afrimmlu_direct
+task: afrimmlu_direct_kin_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+include: afrimmlu_direct
+task: afrimmlu_direct_lin_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+include: afrimmlu_direct
+task: afrimmlu_direct_lug_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+include: afrimmlu_direct
+task: afrimmlu_direct_orm_prompt_5