livebench_language

# Dataset Card for "livebench/language"
LiveBench is a benchmark for LLMs designed with test set contamination and objective evaluation in mind. It has the following properties:
- LiveBench is designed to limit potential contamination by releasing new questions monthly, as well as having questions based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses.
- Each question has verifiable, objective ground-truth answers, allowing hard questions to be scored accurately and automatically, without the use of an LLM judge.
- LiveBench currently contains a set of 18 diverse tasks across 6 categories, and we will release new, harder tasks over time.
This is the instruction_following category of livebench.

See more in our [paper](https://arxiv.org/abs/2406.19314), [leaderboard](https://livebench.ai/), and [datasheet](https://github.com/LiveBench/LiveBench/blob/main/docs/DATASHEET.md).

# 「livebench/language」数据集卡片

LiveBench 是一款专为大语言模型（Large Language Model，LLM）设计的基准测试集，其研发初衷为规避测试集污染问题并实现客观评估。该基准具备以下特性：
- 该基准通过每月发布全新题目，以及基于最新公开数据集、arXiv论文、新闻文章与IMDb电影剧情概要构建题目，以此限制潜在的测试集污染。
- 每道题目均配有可验证的客观标准答案，无需借助大语言模型作为评判器，即可对高难度题目实现精准且自动化的评分。
- 当前LiveBench 涵盖6个类别下共18项多样化任务，后续还将逐步发布难度更高的全新任务。

本数据集属于LiveBench的指令跟随（instruction_following）类别。

更多详情可参阅我们的[论文](https://arxiv.org/abs/2406.19314)、[排行榜](https://livebench.ai/)以及[数据集说明文档](https://github.com/LiveBench/LiveBench/blob/main/docs/DATASHEET.md)。