[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

Bench: Extending Long Context Evaluation Beyond 100K Tokens

Xinrong Zhang, Yingfa Chen, Shengding Hu, Zihang Xu, Junhao Chen, Moo Hao, Xu Han, Zhen Thai, Shuo Wang, Zhiyuan Liu, Maosong Sun


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. comprises synthetic and realistic tasks spanning diverse domains in English and Chinese. The tasks in are designed to require an understanding of long dependencies in contexts and make simply retrieving a limited number of passages from contexts not sufficient for these tasks. Based on , we evaluate several state-of-the-art LLMs tailored for processing long contexts. The experimental results indicate that existing long-context LLMs still require significant advancements to process 100K+ contexts effectively. Furthermore, we present three intriguing analyses regarding the behavior of LLMs processing long context. Our code and data is released.
Anthology ID:
2024.acl-long.814
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15262–15277
Language:
URL:
https://aclanthology.org/2024.acl-long.814
DOI:
10.18653/v1/2024.acl-long.814
Bibkey:
Cite (ACL):
Xinrong Zhang, Yingfa Chen, Shengding Hu, Zihang Xu, Junhao Chen, Moo Hao, Xu Han, Zhen Thai, Shuo Wang, Zhiyuan Liu, and Maosong Sun. 2024. ∞Bench: Extending Long Context Evaluation Beyond 100K Tokens. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15262–15277, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
∞Bench: Extending Long Context Evaluation Beyond 100K Tokens (Zhang et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.814.pdf