ICML 2026收录：为LLM智能体设计的分层记忆增强安全护栏，提升复杂场景下的行为可控性。
arXiv:2605.05704v2 Announce Type: replace-cross Abstract: Recent advances in foundation models have transformed LLMs from passive conversational syste…
揭秘多语言下AI安全护栏失效的根本原因，从数据分布到tokenization的深度剖析。
arXiv:2605.17173v1 Announce Type: cross Abstract: Large language models exhibit safety degradation in non-English languages. Standard evaluation relie…
开源本地安全护栏，阻挡AI编码代理的破坏性操作，v0.7新增45+自适应规则与更多测试用例。
Article URL: https://github.com/AperionAI/shield Comments URL: https://news.ycombinator.com/item?id=48207471 Points: 2 # Comments: 0