📄 Single Turn With Reference Gpt4 Judgement¶

Note

ID: cards.mt_bench.response_assessment.rating.single_turn_with_reference_gpt4_judgement | Type: TaskCard

{
    "__type__": "task_card",
    "loader": {
        "__type__": "load_from_hf_space",
        "data_files": {
            "judgment": "data/mt_bench/model_judgment/gpt-4_single.jsonl",
            "model_answer": "data/mt_bench/model_answer/*.jsonl",
            "questions": "data/mt_bench/question.jsonl"
        },
        "revision": "a4b674c",
        "space_name": "lmsys/mt-bench"
    },
    "preprocess_steps": [
        "operators.mt_bench.rating_hf_space_processing_steps",
        {
            "__type__": "filter_by_condition",
            "condition": "eq",
            "values": {
                "turn": 1
            }
        },
        {
            "__type__": "filter_by_condition",
            "condition": "ne",
            "values": {
                "reference": null
            }
        },
        {
            "__type__": "rename_fields",
            "field_to_field": {
                "category": "group",
                "model_input": "question",
                "model_output": "answer",
                "reference": "reference_answer",
                "score": "rating"
            }
        },
        {
            "__type__": "copy",
            "field": "question/0",
            "to_field": "question"
        },
        {
            "__type__": "copy",
            "field": "answer/0",
            "to_field": "answer"
        },
        {
            "__type__": "copy",
            "field": "reference_answer/0",
            "to_field": "reference_answer"
        }
    ],
    "task": "tasks.response_assessment.rating.single_turn_with_reference",
    "templates": [
        "templates.response_assessment.rating.mt_bench_single_turn_with_reference"
    ]
}

Explanation about TaskCard¶

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

Attributes:
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 a 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 LoadFromHFSpace¶

Used to load data from Huggingface spaces.

Loaders firstly tries to download all files specified in the ‘data_files’ parameter from the given space and then reads them as a Huggingface dataset.
Args:
space_name (str): Name of the Huggingface space to be accessed to. data_files (str | Sequence[str] | Mapping[str, str | Sequence[str]]): Relative

paths to files within a given repository. If given as a mapping, paths should be values, while keys should represent the type of respective files (training, testing etc.).

path (str, optional): Absolute path to a directory where data should be downloaded to. revision (str, optional): ID of a Git branch or commit to be used. By default, it is

set to None, thus data is downloaded from the main branch of the accessed repository.

use_token (bool, optional): Whether token used for authentication when accessing
the Huggingface space - if necessary - should be read from the Huggingface config folder.

token_env (str, optional): Key of an env variable which value will be used for
authentication when accessing the Huggingface space - if necessary.

Example:
Loading from Huggingface Space
loader = LoadFromHFSpace(
    space_name="lmsys/mt-bench",
    data_files={
        "train": [
            "data/mt_bench/model_answer/gpt-3.5-turbo.jsonl",
            "data/mt_bench/model_answer/gpt-4.jsonl",
        ],
        "test": "data/mt_bench/model_answer/tulu-30b.jsonl",
    },
)

Explanation about FilterByCondition¶

Filters a stream, yielding only instances in which the values in required fields follow the required condition operator.

Raises an error if a required field name is missing from the input instance.

Args:
values (Dict[str, Any]): Field names and respective Values that instances must match according the condition, to be included in the output. condition: the name of the desired condition operator between the specified (sub) field’s value and the provided constant value. Supported conditions are (“gt”, “ge”, “lt”, “le”, “ne”, “eq”, “in”,”not in”) error_on_filtered_all (bool, optional): If True, raises an error if all instances are filtered out. Defaults to True.

Examples:
FilterByCondition(values = {“a”:4}, condition = “gt”) will yield only instances where field “a” contains a value > 4 FilterByCondition(values = {“a”:4}, condition = “le”) will yield only instances where “a”<=4 FilterByCondition(values = {“a”:[4,8]}, condition = “in”) will yield only instances where “a” is 4 or 8 FilterByCondition(values = {“a”:[4,8]}, condition = “not in”) will yield only instances where “a” different from 4 or 8 FilterByCondition(values = {“a/b”:[4,8]}, condition = “not in”) will yield only instances where “a” is

a dict in which key “b” is mapped to a value that is neither 4 nor 8

FilterByCondition(values = {“a[2]”:4}, condition = “le”) will yield only instances where “a” is a list whose 3-rd
element is <= 4

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 RenameFields¶

Renames fields.

Move value from one field to another, potentially, if field name contains a /, from one branch into another. Remove the from field, potentially part of it in case of / in from_field.

Examples:
RenameFields(field_to_field={“b”: “c”}) will change inputs [{“a”: 1, “b”: 2}, {“a”: 2, “b”: 3}] to [{“a”: 1, “c”: 2}, {“a”: 2, “c”: 3}]

RenameFields(field_to_field={“b”: “c/d”}) will change inputs [{“a”: 1, “b”: 2}, {“a”: 2, “b”: 3}] to [{“a”: 1, “c”: {“d”: 2}}, {“a”: 2, “c”: {“d”: 3}}]

RenameFields(field_to_field={“b”: “b/d”}) will change inputs [{“a”: 1, “b”: 2}, {“a”: 2, “b”: 3}] to [{“a”: 1, “b”: {“d”: 2}}, {“a”: 2, “b”: {“d”: 3}}]

RenameFields(field_to_field={“b/c/e”: “b/d”}) will change inputs [{“a”: 1, “b”: {“c”: {“e”: 2, “f”: 20}}}] to [{“a”: 1, “b”: {“c”: {“f”: 20}, “d”: 2}}]

References: tasks.response_assessment.rating.single_turn_with_reference, templates.response_assessment.rating.mt_bench_single_turn_with_reference, operators.mt_bench.rating_hf_space_processing_steps