paper-with-me

Papers

SafetyBench: Evaluating the Safety of Large Language Models

2023-09-13 · Zhexin Zhang, Leqi Lei, Lindong Wu, Rui Sun, Yongkang Huang, Chong Long, Xiao Liu, Xuanyu Lei, Jie Tang, Minlie Huang

With the rapid development of Large Language Models (LLMs), increasing attention has been paid to their safety concerns. Consequently, evaluating the safety of LLMs has become an essential task for facilitating the broad applications of LLMs. Nevertheless, the absence of comprehensive safety evaluation benchmarks poses a significant impediment to effectively assess and enhance the safety of LLMs. In this work, we present SafetyBench, a comprehensive benchmark for evaluating the safety of LLMs, which comprises 11,435 diverse multiple choice questions spanning across 7 distinct categories of safety concerns. Notably, SafetyBench also incorporates both Chinese and English data, facilitating the evaluation in both languages. Our extensive tests over 25 popular Chinese and English LLMs in both zero-shot and few-shot settings reveal a substantial performance advantage for GPT-4 over its counterparts, and there is still significant room for improving the safety of current LLMs. We also demonstrate that the measured safety understanding abilities in SafetyBench are correlated with safety generation abilities. Data and evaluation guidelines are available at \url{https://github.com/thu-coai/SafetyBench}{https://github.com/thu-coai/SafetyBench}. Submission entrance and leaderboard are available at \url{https://llmbench.ai/safety}{https://llmbench.ai/safety}.

📄 PDF Abstract BibTeX arXiv:2309.07045

Code (1)

thu-coai/safetybench 공식 구현 pytorch

Tasks

Multiple-choice

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Agent-SafetyBench: Evaluating the Safety of LLM Agents

2024-12-19 · Zhexin Zhang, Shiyao Cui, Yida Lu, Jingzhuo Zhou 외

As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. Howeve…

CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models

2024-06-14 · Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu, Meijuan An 외

With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention. However, there is a scarcity of Chinese safety benchmarks for LLMs, and the existing safety taxonomi…

Multiple-choiceQuestion Answering

MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models

2024-03-06 · Tessa Han, Aounon Kumar, Chirag Agarwal, Himabindu Lakkaraju

As large language models (LLMs) develop increasingly sophisticated capabilities and find applications in medical settings, it becomes important to assess their medical safety due to their far-reaching implications for pe…

EthicsGeneral Knowledge

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

2026-05-12 · Chang Jin, An Wang, Zeming Wei, Kai Wang 외 arxiv

Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduce…

LongSafetyBench: Long-Context LLMs Struggle with Safety Issues

2024-11-11 · Mianqiu Huang, Xiaoran Liu, Shaojun Zhou, Mozhi Zhang 외

With the development of large language models (LLMs), the sequence length of these models continues to increase, drawing significant attention to long-context language models. However, the evaluation of these models has …