会员服务
Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents
Arxiv
0+阅读 · 10月23日
Training Natural Schemers: RL Can Amplify Oversight-Conditional Behavior
Arxiv
0+阅读 · 10月19日
On the foundations of anthropic reasoning: Implications for life across the universe
Arxiv
0+阅读 · 10月16日
Simple, Faster (min, +) Matrix Multiplication and APSP
Arxiv
0+阅读 · 10月14日
CLIOPATRA: Extracting Private Information from LLM Insights
Arxiv
0+阅读 · 10月13日
Cognifying Education: Mapping AI's transformative role in emotional, creative, and collaborative learning
Arxiv
0+阅读 · 10月10日
AI Persuasion as a Threat to Human Control
Arxiv
0+阅读 · 9月13日
AI Persuasion as a Threat to Human Control
Arxiv
0+阅读 · 9月16日
Verbal tics in frontier language models: A critical review of current releases, research evidence, and public discussion
Arxiv
0+阅读 · 10月1日
Door-in-the-Face Requests and Refusal Behaviour in Large Language Models
Arxiv
0+阅读 · 9月2日
Tastes without distinction: silicon samples and the synthetic construction of tastes
Arxiv
0+阅读 · 8月30日
CompareBench: A Benchmark for Visual Comparison Reasoning in Vision-Language Models
Arxiv
0+阅读 · 8月27日
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
Arxiv
0+阅读 · 7月20日
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
Arxiv
0+阅读 · 8月10日
Governing Delegation to Generative Artificial Intelligence: Human Direction, Work-Related Orientation, and Modes of Use
Arxiv
0+阅读 · 8月18日
参考链接
微信扫码咨询专知VIP会员
Top