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/afrobench/afriqa/prompt_1/afriqa

+tag:
+    - afrobench_xqa_tasks
+    - afriqa_prompt_1
+dataset_kwargs: {trust_remote_code: True}
+dataset_path: masakhane/afriqa-gold-passages
+dataset_name: null
+output_type: generate_until
+test_split: test
+fewshot_split: train
+doc_to_target: answer_pivot
+should_decontaminate: true
+doc_to_decontamination_query: question_lang
+generation_kwargs:
+  until:
+    - "\n"
+  do_sample: false
+  temperature: 0.0
+filter_list:
+  - name: remove_whitespace
+    filter:
+      - function: remove_whitespace
+      - function: take_first
+target_delimiter: " "
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+      - "."
+      - ","
+      - "\\$"
+  - metric: f1
+    aggregation: !function utils.f1
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+      - "."
+      - ","
+      - "\\$"
+metadata:
+  version: 1.0

lm_eval/tasks/afrobench/afriqa/prompt_1/afriqa_bem.yaml

+# Generated by utils.py
+dataset_name: bem
+doc_to_text: 'Your task is to answer a qestion given a context.Make sure you respond
+  with the shortest span containing the answer in the context.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_bem_prompt_1

lm_eval/tasks/afrobench/afriqa/prompt_1/afriqa_fon.yaml

+# Generated by utils.py
+dataset_name: fon
+doc_to_text: 'Your task is to answer a qestion given a context.Make sure you respond
+  with the shortest span containing the answer in the context.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_fon_prompt_1

lm_eval/tasks/afrobench/afriqa/prompt_1/afriqa_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+doc_to_text: 'Your task is to answer a qestion given a context.Make sure you respond
+  with the shortest span containing the answer in the context.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_hau_prompt_1

lm_eval/tasks/afrobench/afriqa/prompt_1/afriqa_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+doc_to_text: 'Your task is to answer a qestion given a context.Make sure you respond
+  with the shortest span containing the answer in the context.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_ibo_prompt_1

lm_eval/tasks/afrobench/afriqa/prompt_1/afriqa_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+doc_to_text: 'Your task is to answer a qestion given a context.Make sure you respond
+  with the shortest span containing the answer in the context.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_kin_prompt_1

lm_eval/tasks/afrobench/afriqa/prompt_1/afriqa_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+doc_to_text: 'Your task is to answer a qestion given a context.Make sure you respond
+  with the shortest span containing the answer in the context.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+fewshot_split: test
+fewshot_config:
+  sampler: first_n
+task: afriqa_swa_prompt_1

lm_eval/tasks/afrobench/afriqa/prompt_1/afriqa_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+doc_to_text: 'Your task is to answer a qestion given a context.Make sure you respond
+  with the shortest span containing the answer in the context.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_twi_prompt_1

lm_eval/tasks/afrobench/afriqa/prompt_1/afriqa_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+doc_to_text: 'Your task is to answer a qestion given a context.Make sure you respond
+  with the shortest span containing the answer in the context.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_yor_prompt_1

lm_eval/tasks/afrobench/afriqa/prompt_1/afriqa_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+doc_to_text: 'Your task is to answer a qestion given a context.Make sure you respond
+  with the shortest span containing the answer in the context.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_zul_prompt_1

lm_eval/tasks/afrobench/afriqa/prompt_1/utils.py

+import re
+import string
+from collections import Counter
+
+
+def normalize_answer(s):
+    """
+    Taken from the official evaluation script for v1.1 of the SQuAD dataset.
+    Lower text and remove punctuation, articles and extra whitespace.
+    """
+
+    def remove_articles(text):
+        return re.sub(r"\b(a|an|the)\b", " ", text)
+
+    def white_space_fix(text):
+        return " ".join(text.split())
+
+    def remove_punc(text):
+        exclude = set(string.punctuation)
+        return "".join(ch for ch in text if ch not in exclude)
+
+    def lower(text):
+        return text.lower()
+
+    return white_space_fix(remove_articles(remove_punc(lower(s))))
+
+
+def f1(items):
+    """
+    Taken from the official evaluation script for v1.1 of the SQuAD dataset.
+    """
+
+    unzipped_list = list(zip(*items))
+    golds = unzipped_list[0]
+    preds = unzipped_list[1]
+
+    f1_list = []
+
+    for i in range(len(golds)):
+        prediction_tokens = normalize_answer(preds[i]).split()
+        references_tokens = normalize_answer(golds[i]).split()
+        common = Counter(prediction_tokens) & Counter(references_tokens)
+        num_same = sum(common.values())
+        if num_same == 0:
+            f1_score = 0
+        else:
+            precision = 1.0 * num_same / len(prediction_tokens)
+            recall = 1.0 * num_same / len(references_tokens)
+            f1_score = (2 * precision * recall) / (precision + recall)
+
+        f1_list.append(f1_score)
+
+    return sum(f1_list) / len(f1_list)

lm_eval/tasks/afrobench/afriqa/prompt_2/afriqa

+tag:
+    - afrobench_xqa_tasks
+    - afriqa_prompt_2
+dataset_kwargs: {trust_remote_code: True}
+dataset_path: masakhane/afriqa-gold-passages
+dataset_name: null
+output_type: generate_until
+test_split: test
+fewshot_split: train
+doc_to_target: answer_pivot
+should_decontaminate: true
+doc_to_decontamination_query: question_lang
+generation_kwargs:
+  until:
+    - "\n"
+  do_sample: false
+  temperature: 0.0
+filter_list:
+  - name: remove_whitespace
+    filter:
+      - function: remove_whitespace
+      - function: take_first
+target_delimiter: " "
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+      - "."
+      - ","
+      - "\\$"
+  - metric: f1
+    aggregation: !function utils.f1
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+      - "."
+      - ","
+      - "\\$"
+metadata:
+  version: 1.0

lm_eval/tasks/afrobench/afriqa/prompt_2/afriqa_bem.yaml

+# Generated by utils.py
+dataset_name: bem
+doc_to_text: 'Your task is to answer a question given a context. The question is in
+  Bemba, while the context is in English or French.Make sure you respond with the
+  shortest span in the context that contains the answer.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_bem_prompt_2

lm_eval/tasks/afrobench/afriqa/prompt_2/afriqa_fon.yaml

+# Generated by utils.py
+dataset_name: fon
+doc_to_text: 'Your task is to answer a question given a context. The question is in
+  Fon, while the context is in English or French.Make sure you respond with the shortest
+  span in the context that contains the answer.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_fon_prompt_2

lm_eval/tasks/afrobench/afriqa/prompt_2/afriqa_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+doc_to_text: 'Your task is to answer a question given a context. The question is in
+  Hausa, while the context is in English or French.Make sure you respond with the
+  shortest span in the context that contains the answer.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_hau_prompt_2

lm_eval/tasks/afrobench/afriqa/prompt_2/afriqa_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+doc_to_text: 'Your task is to answer a question given a context. The question is in
+  Igbo, while the context is in English or French.Make sure you respond with the shortest
+  span in the context that contains the answer.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_ibo_prompt_2

lm_eval/tasks/afrobench/afriqa/prompt_2/afriqa_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+doc_to_text: 'Your task is to answer a question given a context. The question is in
+  Kinyarwanda, while the context is in English or French.Make sure you respond with
+  the shortest span in the context that contains the answer.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_kin_prompt_2

lm_eval/tasks/afrobench/afriqa/prompt_2/afriqa_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+doc_to_text: 'Your task is to answer a question given a context. The question is in
+  Swahili, while the context is in English or French.Make sure you respond with the
+  shortest span in the context that contains the answer.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+fewshot_split: test
+fewshot_config:
+  sampler: first_n
+task: afriqa_swa_prompt_2

lm_eval/tasks/afrobench/afriqa/prompt_2/afriqa_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+doc_to_text: 'Your task is to answer a question given a context. The question is in
+  Twi, while the context is in English or French.Make sure you respond with the shortest
+  span in the context that contains the answer.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_twi_prompt_2

lm_eval/tasks/afrobench/afriqa/prompt_2/afriqa_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+doc_to_text: 'Your task is to answer a question given a context. The question is in
+  Yoruba, while the context is in English or French.Make sure you respond with the
+  shortest span in the context that contains the answer.
+
+  Question: {{question_lang}}
+
+  Context: {{context}}
+
+  Answer:'
+include: afriqa
+task: afriqa_yor_prompt_2