진실한_qa

참고자료:

세대

TFDS에 이 데이터세트를 로드하려면 다음 명령어를 사용하세요.

ds = tfds.load('huggingface:truthful_qa/generation')
  • 설명 :
TruthfulQA is a benchmark to measure whether a language model is truthful in
generating answers to questions. The benchmark comprises 817 questions that
span 38 categories, including health, law, finance and politics. Questions are
crafted so that some humans would answer falsely due to a false belief or
misconception. To perform well, models must avoid generating false answers
learned from imitating human texts.
  • 라이센스 : 아파치 라이센스 2.0
  • 버전 : 1.1.0
  • 분할 :
나뉘다
'validation' 817
  • 특징 :
{
    "type": {
        "dtype": "string",
        "id": null,
        "_type": "Value"
    },
    "category": {
        "dtype": "string",
        "id": null,
        "_type": "Value"
    },
    "question": {
        "dtype": "string",
        "id": null,
        "_type": "Value"
    },
    "best_answer": {
        "dtype": "string",
        "id": null,
        "_type": "Value"
    },
    "correct_answers": {
        "feature": {
            "dtype": "string",
            "id": null,
            "_type": "Value"
        },
        "length": -1,
        "id": null,
        "_type": "Sequence"
    },
    "incorrect_answers": {
        "feature": {
            "dtype": "string",
            "id": null,
            "_type": "Value"
        },
        "length": -1,
        "id": null,
        "_type": "Sequence"
    },
    "source": {
        "dtype": "string",
        "id": null,
        "_type": "Value"
    }
}

다중 선택

TFDS에 이 데이터세트를 로드하려면 다음 명령어를 사용하세요.

ds = tfds.load('huggingface:truthful_qa/multiple_choice')
  • 설명 :
TruthfulQA is a benchmark to measure whether a language model is truthful in
generating answers to questions. The benchmark comprises 817 questions that
span 38 categories, including health, law, finance and politics. Questions are
crafted so that some humans would answer falsely due to a false belief or
misconception. To perform well, models must avoid generating false answers
learned from imitating human texts.
  • 라이센스 : 아파치 라이센스 2.0
  • 버전 : 1.1.0
  • 분할 :
나뉘다
'validation' 817
  • 특징 :
{
    "question": {
        "dtype": "string",
        "id": null,
        "_type": "Value"
    },
    "mc1_targets": {
        "choices": {
            "feature": {
                "dtype": "string",
                "id": null,
                "_type": "Value"
            },
            "length": -1,
            "id": null,
            "_type": "Sequence"
        },
        "labels": {
            "feature": {
                "dtype": "int32",
                "id": null,
                "_type": "Value"
            },
            "length": -1,
            "id": null,
            "_type": "Sequence"
        }
    },
    "mc2_targets": {
        "choices": {
            "feature": {
                "dtype": "string",
                "id": null,
                "_type": "Value"
            },
            "length": -1,
            "id": null,
            "_type": "Sequence"
        },
        "labels": {
            "feature": {
                "dtype": "int32",
                "id": null,
                "_type": "Value"
            },
            "length": -1,
            "id": null,
            "_type": "Sequence"
        }
    }
}