Back to datasets
Dataset assetOpen Source CommunityNatural Language ProcessingChinese Linguistics

FlagEval/CLCC_v1

CLCC is a Chinese linguistics and cognition challenge dataset created by the FlagEval team. Task categories include question answering and text generation, supporting both Chinese and English. Evaluation results can be obtained via human assessment or the judgeLLM model.

Source
hugging_face
Created
Nov 28, 2025
Updated
Jul 29, 2024
Signals
62 views
Availability
Linked source ready
Overview

Dataset description and usage context

CLCC Dataset Overview

Basic Information

  • License: Apache 2.0
  • Task Categories:
    • Question Answering
    • Text Generation
  • Languages:
    • Chinese
    • English

Data Source

  • Creator: FlagEval Team
  • Details: Available on the FlagEval official website.

Evaluation Method

  • Approach: Human evaluation or using the judgeLLM model.
Need downstream help?

Pair the dataset with AI analysis and content workflows.

Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.

Explore AI studio