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/en_cot/afrimgsm_en_cot_zul.yaml

-# Generated by utils.py
-dataset_name: zul
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_zul

lm_eval/tasks/afrimgsm/en_cot/cot_yaml

-# This file will be included in the generated language-specific task configs.
-# It doesn't have a yaml file extension as it is not meant to be imported directly by the harness.
-tag:
-    - afrimgsm
-    - afrimgsm_en_cot
-dataset_path: masakhane/afrimgsm
-dataset_name: null  # Overridden by language-specific config.
-output_type: generate_until
-training_split: train
-test_split: test
-generation_kwargs:
-  until:
-    - "\n\n"
-    - "\n"
-  do_sample: false
-  temperature: 0.0
-target_delimiter: " "
-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/gen_utils.py

+import argparse
+import os
+
+import yaml
+
+
+class FunctionTag:
+    def __init__(self, value):
+        self.value = value
+
+
+def prompt_func(mode, lang):
+    prompt_map = {
+        "prompt_4": "Answer the given question with the step by step solution appropriate numerical value, ensuring that the response is "
+        "clear and without any supplementary information. \n\nQuestion: {{question}} \nStep by step answer: ",
+        "prompt_5": f"For mathematical questions provided in {lang} language. Supply the accurate step by step answer to the "
+        "provided question. \n\nQuestion: {{question}} \nStep by step answer: ",
+    }
+    return prompt_map[mode]
+
+
+def gen_lang_yamls(output_dir: str, overwrite: bool, mode: str) -> None:
+    """
+    Generate a yaml file for each language.
+
+    :param output_dir: The directory to output the files to.
+    :param overwrite: Whether to overwrite files if they already exist.
+    """
+    err = []
+    languages = {
+        "eng": "English",
+        "amh": "Amharic",
+        "ibo": "Igbo",
+        "fra": "French",
+        "sna": "chiShona",
+        "wol": "Wolof",
+        "ewe": "Ewe",
+        "lin": "Lingala",
+        "lug": "Luganda",
+        "xho": "isiXhosa",
+        "kin": "Kinyarwanda",
+        "twi": "Twi",
+        "zul": "Zulu",
+        "orm": "Oromo",
+        "yor": "Yoruba",
+        "hau": "Hausa",
+        "sot": "Sesotho",
+        "swa": "Swahili",
+        "vai": "Vai",
+    }
+
+    for lang in languages.keys():
+        try:
+            file_name = f"afrimgsm_cot_{lang}.yaml"
+            task_name = f"afrimgsm_cot_{lang}_{mode}"
+            yaml_template = "afrimgsm_cot_yaml"
+            if "translate" in output_dir.split("/")[-1]:
+                file_name = f"afrimgsm_cot_translate_{lang}.yaml"
+                task_name = f"afrimgsm_cot_translate_{lang}_{mode}"
+                yaml_template = "afrimgsm_cot_translate_yaml"
+            if int(mode.split("_")[-1]) > 3:
+                yaml_details = {
+                    "include": yaml_template,
+                    "task": task_name,
+                    "dataset_name": lang,
+                    "doc_to_text": prompt_func(mode, languages[lang]),
+                }
+            else:
+                yaml_details = {
+                    "include": yaml_template,
+                    "task": task_name,
+                    "dataset_name": lang,
+                }
+            os.makedirs(f"{output_dir}/{mode}", exist_ok=True)
+            with open(
+                f"{output_dir}/{mode}/{file_name}",
+                "w" if overwrite else "x",
+                encoding="utf8",
+            ) as f:
+                f.write("# Generated by utils.py\n")
+                yaml.dump(
+                    yaml_details,
+                    f,
+                    allow_unicode=True,
+                )
+        except FileExistsError:
+            err.append(file_name)
+
+    if len(err) > 0:
+        raise FileExistsError(
+            "Files were not created because they already exist (use --overwrite flag):"
+            f" {', '.join(err)}"
+        )
+
+
+def main() -> None:
+    """Parse CLI args and generate language-specific yaml files."""
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--overwrite",
+        default=True,
+        action="store_true",
+        help="Overwrite files if they already exist",
+    )
+    parser.add_argument(
+        "--output-dir",
+        default="./translate_cot",
+        help="Directory to write yaml files to",
+    )
+    parser.add_argument(
+        "--mode",
+        default="prompt_5",
+        choices=["prompt_1", "prompt_2", "prompt_3", "prompt_4", "prompt_5"],
+        help="Prompt number",
+    )
+    args = parser.parse_args()
+
+    gen_lang_yamls(output_dir=args.output_dir, overwrite=args.overwrite, mode=args.mode)
+
+
+if __name__ == "__main__":
+    main()

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_amh.yaml

-# Generated by utils.py
-dataset_name: amh
-doc_to_target: '{% if answer is not none %}{{answer[15:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_amh

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_eng.yaml

-# Generated by utils.py
-dataset_name: eng
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_eng

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_ewe.yaml

-# Generated by utils.py
-dataset_name: ewe
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_ewe

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_fra.yaml

-# Generated by utils.py
-dataset_name: fra
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_fra

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_hau.yaml

-# Generated by utils.py
-dataset_name: hau
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_hau

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_ibo.yaml

-# Generated by utils.py
-dataset_name: ibo
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_ibo

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_kin.yaml

-# Generated by utils.py
-dataset_name: kin
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_kin

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_lin.yaml

-# Generated by utils.py
-dataset_name: lin
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_lin

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_lug.yaml

-# Generated by utils.py
-dataset_name: lug
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_lug

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_orm.yaml

-# Generated by utils.py
-dataset_name: orm
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_orm

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_sna.yaml

-# Generated by utils.py
-dataset_name: sna
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_sna

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_sot.yaml

-# Generated by utils.py
-dataset_name: sot
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_sot

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_swa.yaml

-# Generated by utils.py
-dataset_name: swa
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_swa

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_twi.yaml

-# Generated by utils.py
-dataset_name: twi
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_twi

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_wol.yaml

-# Generated by utils.py
-dataset_name: wol
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_wol

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_xho.yaml

-# Generated by utils.py
-dataset_name: xho
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_xho

lm_eval/tasks/afrimgsm/translate/afrimgsm_translate_yor.yaml

-# Generated by utils.py
-dataset_name: yor
-doc_to_target: '{% if answer is not none %}{{answer[16:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: translate_direct_yaml
-task: afrimgsm_translate_direct_yor