研究库 论文知识库
Papers · organized/paper_cards

论文

3 张论文卡片 · 安全与风险 · 综述 · OA 绿色

开放获取 全部 绿色 · 1640
Cyber Security Awareness Campaigns: Why do they fail to change behaviour?
网络安全意识宣传活动:为何它们未能改变行为?
arXiv:1901.02672 安全与风险 综述 OA · 绿色 被引 465 · S2

综述了包括广泛使用的"恐惧诉求"在内的说服技巧的适用性,并提炼出意识宣传活动的基本要素以及导致活动成败的关键因素。The suitability of persuasion techniques, including the widely used 'fear appeals', are reviewed, and essential components for an awareness campaign as well as factors which can lead to a campaign's success or failure are extracted.

Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
AI 海洋中的海妖之歌:大语言模型幻觉问题综述
arXiv:2309.01219 安全与风险 综述 OA · 绿色 被引 1186 · S2

本文给出了 LLM 幻觉现象与评估基准的分类体系,分析了现有缓解 LLM 幻觉的方法,并讨论了未来研究的潜在方向。This paper presents taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyzes existing approaches aiming at mitigating LLm hallucination, and discusses potential directions for future research.

A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
大语言模型中的幻觉综述:原理、分类、挑战与开放问题
arXiv:2311.05232 安全与风险 综述 OA · 绿色 被引 3939 · S2

全面概述了 LLM 幻觉检测方法与基准,并指出 LLM 幻觉领域有前景的研究方向,包括大视觉-语言模型中的幻觉以及 LLM 幻觉中的知识边界理解。A thorough overview of hallucination detection methods and benchmarks is presented and the promising research directions on LLM hallucinations are highlighted, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.