real_toxicity_prompts

  • 설명 :

RealToxicityPrompts: 언어 모델에서 신경 독성 변성 평가

RealToxicityPrompts는 다양한 독성을 지닌 영어 프롬프트(특히 문장 시작)의 모음입니다. 이러한 프롬프트는 자동 회귀 언어 모델(예: GPT-2)에 대한 컨텍스트로 제공되고 완성을 생성하는 데 사용됩니다.

자세한 내용은 원본 논문 에 나와 있습니다.

나뉘다
'train' 99,442
  • 기능 구조 :
FeaturesDict({
    'begin': int32,
    'challenging': bool,
    'continuation': FeaturesDict({
        'flirtation': float32,
        'identity_attack': float32,
        'insult': float32,
        'profanity': float32,
        'severe_toxicity': float32,
        'sexually_explicit': float32,
        'text': Text(shape=(), dtype=string),
        'threat': float32,
        'toxicity': float32,
    }),
    'end': int32,
    'filename': Text(shape=(), dtype=string),
    'prompt': FeaturesDict({
        'flirtation': float32,
        'identity_attack': float32,
        'insult': float32,
        'profanity': float32,
        'severe_toxicity': float32,
        'sexually_explicit': float32,
        'text': Text(shape=(), dtype=string),
        'threat': float32,
        'toxicity': float32,
    }),
})
  • 기능 문서 :
특징 수업 모양 Dtype 설명
특징Dict
시작하다 텐서 정수32
도전적인 텐서 부울
계속 특징Dict
계속/희롱 텐서 float32
연속/identity_attack 텐서 float32
계속/모욕 텐서 float32
계속/욕설 텐서 float32
지속/심각한_독성 텐서 float32
계속/성적으로 노골적인 텐서 float32
계속/텍스트 텍스트
지속/위협 텐서 float32
지속성/독성 텐서 float32
텐서 정수32
파일 이름 텍스트
즉각적인 특징Dict
프롬프트/희롱 텐서 float32
프롬프트/identity_attack 텐서 float32
프롬프트/모욕 텐서 float32
프롬프트/욕설 텐서 float32
프롬프트/심각한_독성 텐서 float32
프롬프트/성적으로 노골적인 텐서 float32
프롬프트/텍스트 텍스트
프롬프트/위협 텐서 float32
프롬프트/독성 텐서 float32
@article{gehman2020realtoxicityprompts,
  title={Realtoxicityprompts: Evaluating neural toxic degeneration in language models},
  author={Gehman, Samuel and Gururangan, Suchin and Sap, Maarten and Choi, Yejin and Smith, Noah A},
  journal={arXiv preprint arXiv:2009.11462},
  year={2020}
}