📄 Human Eval¶

BIGGEN-Bench (BiG Generation Benchmark) is a comprehensive evaluation benchmark designed to assess the capabilities of large language models (LLMs) across a wide range of tasks. This benchmark focuses on free-form text generation and employs fine-grained, instance-specific evaluation criteria. This card is aimed to be used to benchmark LLM judges using the human evaluations as the ground truth.

cards.biggen_bench.results.human_eval

TaskCard(
    loader=LoadHF(
        path="prometheus-eval/BiGGen-Bench-Results",
        splits=[
            "human_eval",
            "multilingual_human_eval",
        ],
    ),
    preprocess_steps=[
        MergeStreams(
            streams_to_merge=[
                "human_eval",
                "multilingual_human_eval",
            ],
            new_stream_name="test",
            add_origin_stream_name=True,
        ),
        Set(
            fields={
                "criteria": {
                    "name": "",
                    "description": "",
                    "options": [
                        {
                        "name": "score1_description",
                        "description": "",
                        },
                        {
                        "name": "score2_description",
                        "description": "",
                        },
                        {
                        "name": "score3_description",
                        "description": "",
                        },
                        {
                        "name": "score4_description",
                        "description": "",
                        },
                        {
                        "name": "score5_description",
                        "description": "",
                        },
                    ],
                    "prediction_field": "response",
                    "context_fields": [
                        "system_prompt",
                        "input",
                        "reference_answer",
                    ],
                    "option_map": {
                        "score1_description": 0.0,
                        "score2_description": 0.25,
                        "score3_description": 0.5,
                        "score4_description": 0.75,
                        "score5_description": 1.0,
                    },
                },
            },
        ),
        Cast(
            field="human_score",
            to="float",
        ),
        Copy(
            field_to_field={
                "task": "criteria/name",
                "score_rubric/criteria": "criteria/description",
                "score_rubric/score1_description": "criteria/options/0/description",
                "score_rubric/score2_description": "criteria/options/1/description",
                "score_rubric/score3_description": "criteria/options/2/description",
                "score_rubric/score4_description": "criteria/options/3/description",
                "score_rubric/score5_description": "criteria/options/4/description",
            },
        ),
        CreateCriteriaWithOptionsFromDict(
            field="criteria",
        ),
    ],
    task=Task(
        input_fields={
            "system_prompt": "str",
            "input": "str",
            "response": "str",
            "reference_answer": "str",
            "criteria": "Any",
        },
        reference_fields={
            "human_score": "float",
        },
        prediction_type="float",
        metrics=[
            "metrics.spearman",
            "metrics.pearson",
        ],
        default_template="templates.empty[postprocessors=[processors.cast_to_float_return_nan_if_failed]]",
    ),
    templates=[],
)

[source]

from unitxt.llm_as_judge_operators import CreateCriteriaWithOptionsFromDict
from unitxt.loaders import LoadHF
from unitxt.operators import Cast, Copy, MergeStreams, Set
from unitxt.task import Task

Explanation about TaskCard¶

TaskCard delineates the phases in transforming the source dataset into model input, and specifies the metrics for evaluation of model output.

Args:

loader:
specifies the source address and the loading operator that can access that source and transform it into a unitxt multistream.

preprocess_steps:
list of unitxt operators to process the data source into model input.

task:
specifies the fields (of the already (pre)processed instance) making the inputs, the fields making the outputs, and the metrics to be used for evaluating the model output.

templates:
format strings to be applied on the input fields (specified by the task) and the output fields. The template also carries the instructions and the list of postprocessing steps, to be applied to the model output.

Explanation about Copy¶

Copies values from specified fields to specified fields.

Args (of parent class):
field_to_field (Union[List[List], Dict[str, str]]): A list of lists, where each sublist contains the source field and the destination field, or a dictionary mapping source fields to destination fields.

Examples:
An input instance {“a”: 2, “b”: 3}, when processed by Copy(field_to_field={"a": "b"}) would yield {“a”: 2, “b”: 2}, and when processed by Copy(field_to_field={"a": "c"}) would yield {“a”: 2, “b”: 3, “c”: 2}

with field names containing / , we can also copy inside the field: Copy(field="a/0",to_field="a") would process instance {“a”: [1, 3]} into {“a”: 1}

Explanation about MergeStreams¶

Merges multiple streams into a single stream.

Args:
new_stream_name (str): The name of the new stream resulting from the merge. add_origin_stream_name (bool): Whether to add the origin stream name to each instance. origin_stream_name_field_name (str): The field name for the origin stream name.

Explanation about Cast¶

Casts specified fields to specified types.

Args:
default (object): A dictionary mapping field names to default values for cases of casting failure. process_every_value (bool): If true, all fields involved must contain lists, and each value in the list is then casted. Defaults to False.

Explanation about LoadHF¶

Loads datasets from the HuggingFace Hub.

It supports loading with or without streaming, and it can filter datasets upon loading.
Args:

path:
The path or identifier of the dataset on the HuggingFace Hub.

name:
An optional dataset name.

data_dir:
Optional directory to store downloaded data.

split:
Optional specification of which split to load.

data_files:
Optional specification of particular data files to load. When you provide a list of data_files to Hugging Face’s load_dataset function without explicitly specifying the split argument, these files are automatically placed into the train split.

revision:
Optional. The revision of the dataset. Often the commit id. Use in case you want to set the dataset version.

streaming (bool):
indicating if streaming should be used.

filtering_lambda (str, optional):
A lambda function for filtering the data after loading.

num_proc (int, optional):
Specifies the number of processes to use for parallel dataset loading.

Example:
Loading glue’s mrpc dataset
load_hf = LoadHF(path='glue', name='mrpc')

Explanation about Task¶

Task packs the different instance fields into dictionaries by their roles in the task.

Args:

input_fields (Union[Dict[str, str], List[str]]):
Dictionary with string names of instance input fields and types of respective values. In case a list is passed, each type will be assumed to be Any.

reference_fields (Union[Dict[str, str], List[str]]):
Dictionary with string names of instance output fields and types of respective values. In case a list is passed, each type will be assumed to be Any.

metrics (List[str]):
List of names of metrics to be used in the task.

prediction_type (Optional[str]):
Need to be consistent with all used metrics. Defaults to None, which means that it will be set to Any.

defaults (Optional[Dict[str, Any]]):
An optional dictionary with default values for chosen input/output keys. Needs to be consistent with names and types provided in ‘input_fields’ and/or ‘output_fields’ arguments. Will not overwrite values if already provided in a given instance.

The output instance contains three fields:

“input_fields” whose value is a sub-dictionary of the input instance, consisting of all the fields listed in Arg ‘input_fields’.

“reference_fields” – for the fields listed in Arg “reference_fields”.

“metrics” – to contain the value of Arg ‘metrics’

Explanation about Set¶

Sets specified fields in each instance, in a given stream or all streams (default), with specified values. If fields exist, updates them, if do not exist – adds them.

Args:
fields (Dict[str, object]): The fields to add to each instance. Use ‘/’ to access inner fields

use_deepcopy (bool) : Deep copy the input value to avoid later modifications

Examples:
# Set a value of a list consisting of “positive” and “negative” do field “classes” to each and every instance of all streams Set(fields={"classes": ["positive","negatives"]})

# In each and every instance of all streams, field “span” is to become a dictionary containing a field “start”, in which the value 0 is to be set Set(fields={"span/start": 0}

# In all instances of stream “train” only, Set field “classes” to have the value of a list consisting of “positive” and “negative” Set(fields={"classes": ["positive","negatives"], apply_to_stream=["train"]})

# Set field “classes” to have the value of a given list, preventing modification of original list from changing the instance. Set(fields={"classes": alist}), use_deepcopy=True) if now alist is modified, still the instances remain intact.

References: processors.cast_to_float_return_nan_if_failed, metrics.spearman, templates.empty, metrics.pearson