牛哥精选 · 本月

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

📝 深度技术 arXiv NLP 2026-06-12

Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation

用波斯谚语约束大模型生成故事，探索语义解压缩新路径，研究巧妙且有趣

arXiv:2606.12599v1 Announce Type: new Abstract: Transforming a dense, abstract proverb into an engaging and morally faithful narrative requires deep c…

llm 语义解压缩波斯谚语故事生成约束生成

🤖 AI·大模型 arXiv NLP 2026-06-01

ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails

提出 ConsisGuard 方法，对齐安全审议与策略执行，提升大模型护栏的可靠性与一致性。

arXiv:2605.31073v1 Announce Type: new Abstract: Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issu…

consisguar llm安全护栏政策对齐约束生成 ai安全

📝 深度技术 arXiv NLP 2026-05-26

Schema-Grounded LLM Extraction for FHIR Patient Digital Twins

用LLM约束生成FHIR bundle，实现患者数字孪生的自洽构建，省去级联模块。

arXiv:2601.05847v2 Announce Type: replace Abstract: We revisit the problem of constructing interoperable patient digital twins from unstructured elect…

llm fhir 数字孪生电子健康记录信息抽取

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation

ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails

Schema-Grounded LLM Extraction for FHIR Patient Digital Twins

📅 日期