Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 1편

HC3

HC3 설명 보기

The HC3 (Human ChatGPT Comparison Corpus) dataset consists of nearly 40K questions and their corresponding human/ChatGPT answers. The motivation for this dataset was to study ChatGPT's answers in contrast to human's answers. The questions range from a wide variety of domains, including open-domain, financial, medical, legal, and psychological areas.

관련 논문 2편

HC3 Plus

HC3 Plus 설명 보기

In order to fill the gap of HC3 under semanticinvariant tasks, we extend HC3 and propose a larger ChatGPT-generated text dataset covering translation, summarization, and paraphrasing tasks, called HC3 Plus.