Saved in:
Bibliographic Details
Main Authors: Li, Yudong, Yang, Peiru, Huang, Feng, Yang, Zhongliang, Wang, Kecheng, Li, Haitian, Chen, Baocheng, An, Xingyu, Liu, Ziyu, Yang, Youdan, Chen, Kejiang, Wan, Sifang, Wang, Xu, Sun, Yufei, Wu, Liyan, Zhou, Ruiqi, Wen, Wenya, Gu, Xingchi, Zhang, Tianxin, Gao, Yue, Huang, Yongfeng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.02366
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914211622289408
author Li, Yudong
Yang, Peiru
Huang, Feng
Yang, Zhongliang
Wang, Kecheng
Li, Haitian
Chen, Baocheng
An, Xingyu
Liu, Ziyu
Yang, Youdan
Chen, Kejiang
Wan, Sifang
Wang, Xu
Sun, Yufei
Wu, Liyan
Zhou, Ruiqi
Wen, Wenya
Gu, Xingchi
Zhang, Tianxin
Gao, Yue
Huang, Yongfeng
author_facet Li, Yudong
Yang, Peiru
Huang, Feng
Yang, Zhongliang
Wang, Kecheng
Li, Haitian
Chen, Baocheng
An, Xingyu
Liu, Ziyu
Yang, Youdan
Chen, Kejiang
Wan, Sifang
Wang, Xu
Sun, Yufei
Wu, Liyan
Zhou, Ruiqi
Wen, Wenya
Gu, Xingchi
Zhang, Tianxin
Gao, Yue
Huang, Yongfeng
contents We introduce LiveSecBench, a continuously updated safety benchmark specifically for Chinese-language LLM application scenarios. LiveSecBench constructs a high-quality and unique dataset through a pipeline that combines automated generation with human verification. By periodically releasing new versions to expand the dataset and update evaluation metrics, LiveSecBench provides a robust and up-to-date standard for AI safety. In this report, we introduce our second release v251215, which evaluates across five dimensions (Public Safety, Fairness & Bias, Privacy, Truthfulness, and Mental Health Safety.) We evaluate 57 representative LLMs using an ELO rating system, offering a leaderboard of the current state of Chinese LLM safety. The result is available at https://livesecbench.intokentech.cn/.
format Preprint
id arxiv_https___arxiv_org_abs_2511_02366
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LiveSecBench: A Dynamic and Event-Driven Safety Benchmark for Chinese Language Model Applications
Li, Yudong
Yang, Peiru
Huang, Feng
Yang, Zhongliang
Wang, Kecheng
Li, Haitian
Chen, Baocheng
An, Xingyu
Liu, Ziyu
Yang, Youdan
Chen, Kejiang
Wan, Sifang
Wang, Xu
Sun, Yufei
Wu, Liyan
Zhou, Ruiqi
Wen, Wenya
Gu, Xingchi
Zhang, Tianxin
Gao, Yue
Huang, Yongfeng
Computation and Language
We introduce LiveSecBench, a continuously updated safety benchmark specifically for Chinese-language LLM application scenarios. LiveSecBench constructs a high-quality and unique dataset through a pipeline that combines automated generation with human verification. By periodically releasing new versions to expand the dataset and update evaluation metrics, LiveSecBench provides a robust and up-to-date standard for AI safety. In this report, we introduce our second release v251215, which evaluates across five dimensions (Public Safety, Fairness & Bias, Privacy, Truthfulness, and Mental Health Safety.) We evaluate 57 representative LLMs using an ELO rating system, offering a leaderboard of the current state of Chinese LLM safety. The result is available at https://livesecbench.intokentech.cn/.
title LiveSecBench: A Dynamic and Event-Driven Safety Benchmark for Chinese Language Model Applications
topic Computation and Language
url https://arxiv.org/abs/2511.02366