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/filters/extraction.py

@@ -54,6 +54,51 @@ class RegexFilter(Filter):
             return filtered
 
         filtered_resps = list(map(lambda x: filter_set(x), resps))
+        return filtered_resps
+
+
+@register_filter("regex_pos")
+class POSFilter(Filter):
+    """ """
+
+    def __init__(
+        self,
+        regex_pattern: str = r"\['(.*?)'\]",
+        group_select=0,
+        fallback=None,
+    ) -> None:
+        """
+        pass a string `regex` to run `re.compile(r"regex")` on.
+        `fallback` defines the output returned if no matches for the regex are located.
+        """
+        if fallback is None:
+            fallback = ["invalid"]
+        self.regex_pattern = regex_pattern
+        self.regex = re.compile(regex_pattern)
+        self.group_select = group_select
+        self.fallback = fallback
+
+    def apply(self, resps, docs):
+        def extract_tagged_tokens(text):
+            # Extract tagged tokens list from text input using regex
+            tokens = re.findall(r"\('([^']*)', '([^']*)'\)", text)
+            return [(token, pos) for token, pos in tokens]
+
+        def extract_pos_tags(result):
+            pos_tags = []
+            if isinstance(result, str):
+                result = extract_tagged_tokens(result)
+            pos_tags.extend(pos for _, pos in result)
+            return pos_tags if pos_tags else self.fallback
+
+        def filter_set(inst):
+            filtered = []
+            for resp in inst:
+                match = extract_pos_tags(resp)
+                filtered.append(match)
+            return filtered
+
+        filtered_resps = map(lambda x: filter_set(x), resps)
 
         return filtered_resps
 

lm_eval/filters/transformation.py

+import re
+
 from lm_eval.api.filter import Filter
 from lm_eval.api.registry import register_filter
 
@@ -54,3 +56,67 @@ class MapFilter(Filter):
             return [self.mapping_dict.get(resp, self.default_value) for resp in inst]
 
         return [filter_set(resp) for resp in resps]
+
+
+@register_filter("format_span")
+class SPANFilter(Filter):
+    def __init__(self) -> None:
+        pass
+
+    def apply(self, resps, docs):
+        def format_ner_text(text):
+            label_dict = {
+                "person": "PER",
+                "location": "LOC",
+                "organization": "ORG",
+                "counties": "LOC",
+                "places": "LOC",
+                "people": "PER",
+                "persons": "PER",
+                "company": "ORG",
+                "country": "LOC",
+                "continent": "LOC",
+                "time": "DATE",
+                "date": "DATE",
+                "per": "PER",
+                "loc": "LOC",
+                "org": "ORG",
+            }
+            text = text.lower()
+            for key, value in label_dict.items():
+                text = text.replace(key, value)
+
+            text = "$".join(i for i in text.split("$$"))
+            return text.rstrip("$$")
+
+        def format_named_entities(text):
+            """
+            Extract named entities from text and format them as 'label: value $$ label: value'.
+            Handles grouped entities (e.g., LOC: kenya, uganda) and excludes 'none' values.
+            """
+            # Regular expression to match label: entities pattern
+            pattern = r"\b(PER|LOC|ORG|DATE):\s*([^$]+)"
+            # Normalize newline characters
+            text = text.replace("\n", "$").strip()
+            matches = re.findall(pattern, text)
+
+            formatted_entities = []
+
+            for label, values in matches:
+                # Split multiple entities separated by commas and strip whitespace
+                entities = [value.strip() for value in values.split(",")]
+
+                # Exclude 'none' entities
+                for entity in entities:
+                    if entity.lower() != "none":
+                        formatted_entities.append(f"{label.lower()}: {entity}")
+
+            # Join entities with the desired separator
+            return " $ ".join(formatted_entities)
+
+        def filter_set(inst):
+            return [
+                format_named_entities(format_ner_text(resp.lower())) for resp in inst
+            ]
+
+        return [filter_set(resp) for resp in resps]

lm_eval/tasks/afrimgsm/direct/afrimgsm.yaml

+group: afrimgsm-irokobench
+task:
+  - afrimgsm_tasks_prompt_1
+  - afrimgsm_tasks_prompt_2
+  - afrimgsm_tasks_prompt_3
+  - afrimgsm_tasks_prompt_4
+  - afrimgsm_tasks_prompt_5
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 2

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_amh

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_eng

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_ewe

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_fra

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_hau

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_ibo

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_kin

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_lin

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_lug

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_orm

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_sna

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_sot

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_swa

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_twi

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_wol

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_xho

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_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: direct_yaml
-task: afrimgsm_direct_yor