{
 "id": "xinrongzhang2022/InfiniteBench",
 "owner": "xinrongzhang2022",
 "name": "InfiniteBench",
 "downloads": 9162,
 "likes": 38,
 "last_modified": "2024-10-08T01:59:10.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "Please cite us if you use $\\infty$Bench.\n\n```bibtex\n@inproceedings{zhang-etal-2024-bench,\n    title = \"$\\infty${B}ench: Extending Long Context Evaluation Beyond 100{K} Tokens\",\n    author = \"Zhang, Xinrong  and\n      Chen, Yingfa  and\n      Hu, Shengding  and\n      Xu, Zihang  and\n      Chen, Junhao  and\n      Hao, Moo  and\n      Han, Xu  and\n      Thai, Zhen  and\n      Wang, Shuo  and\n      Liu, Zhiyuan  and\n      Sun, Maosong\",\n    editor = \"Ku, Lun-Wei  and\n      Martins, Andre  and\n      Srikumar, Vivek\",\n    booktitle = \"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n    month = aug,\n    year = \"2024\",\n    address = \"Bangkok, Thailand\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.acl-long.814\",\n    pages = \"15262--15277\",\n    abstract = \"Processing and reasoning over long contexts is crucial for many practical applications of Large Language Models (LLMs), such as document comprehension and agent construction. Despite recent strides in making LLMs process contexts with more than 100K tokens, there is currently a lack of a standardized benchmark to evaluate this long-context capability. Existing public benchmarks typically focus on contexts around 10K tokens, limiting the assessment and comparison of LLMs in processing longer contexts. In this paper, we propose , the first LLM benchmark featuring an average data length surpassing 100K tokens. compris",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "90f0394333616266d9fe85824ceaf505093cbaa5",
 "stated_evidence": "https://huggingface.co/datasets/xinrongzhang2022/InfiniteBench/blob/90f0394333616266d9fe85824ceaf505093cbaa5/README.md",
 "file_evidence": "https://huggingface.co/datasets/xinrongzhang2022/InfiniteBench/tree/90f0394333616266d9fe85824ceaf505093cbaa5",
 "card_nc": false
}