研究论文开放获取
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Paul Röttger, Hannah Rose Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, Dirk Hovy
Bocconi University University of Oxford Stanford University
来源Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)
年份2024
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
摘要 · 完整
Paul Röttger, Hannah Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, Dirk Hovy. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
逐年被引趋势
50250
24
25
5026
关键指标
76
被引次数 · OpenAlex
34.86
领域内被引倍数
同类平均 = 1
同类平均 = 1
前 0.2%
引用位次
同领域 · 同年份 · 同类型
同领域 · 同年份 · 同类型
0
参考文献
Google Scholar 与 OpenAlex 的被引统计范围不同，数值存在差异属正常。
AI 辅助阅读
依据：摘要
论文问答
当前基于摘要回答
可就本文提问；依据不足时会说明。
学术脉络
学科主题
社会科学Ethics and Social Impacts of AI
Adversarial Robustness in Machine Learning · Natural Language Processing Techniques
参考文献 0
暂无参考文献明细
引用本文 76
Safeguarding large language models: a survey
被引 117Yi Dong, Ronghui Mu, Yanghao Zhang · Artificial Intelligence Review · 2025
Large Language Models for Text Classification: From Zero-Shot Learning to Instruction-Tuning
被引 48Youngjin Chae, Thomas Davidson · Sociological Methods & Research · 2025
(Ir)rationality and cognitive biases in large language models
被引 47Olivia Macmillan-Scott, Mirco Musolesi · Royal Society Open Science · 2024
按被引量排序，此处列出前 3 条