指导大语言模型成为领域自适应、精确和安全的
Tutoring Large Language Models to be Domain-adaptive, Precise, and Safe
AI总结：
本研究通过领域适应、伦理严谨性和文化对齐，指导大语言模型实现精确性、安全性和全球包容性。
摘要：
本研究的核心方向是开发一个''负责任的智能''框架，旨在调和大语言模型（LLMs）的生成能力与现实部署的严格要求。随着这些模型成为人工智能变革性力量，迫切需要超越通用架构，向具有上下文意识、内在安全且深刻尊重全球文化差异的系统发展。本研究贯穿三个相互关联的线索：领域适应以确保技术精确性，伦理严谨性以缓解对抗性漏洞，以及文化/多语言对齐以促进全球包容性。方法论轨迹从经典的监督适应以满足任务特定需求，到解码时对齐以实现安全，最终利用人类反馈和偏好建模以达到社会语言学的敏锐性。
英文摘要：
The overarching research direction of this work is the development of a ''Responsible Intelligence'' framework designed to reconcile the immense generative power of Large Language Models (LLMs) with the stringent requirements of real-world deployment. As these models become a transformative force in artificial intelligence, there is an urgent need to move beyond general-purpose architectures toward systems that are contextually aware, inherently safer, and deeply respectful of global cultural nuances. This research navigates three interconnected threads: domain adaptation to ensure technical precision, ethical rigor to mitigate adversarial vulnerabilities, and cultural/multilingual alignment to promote global inclusivity. The methodological trajectory moves from classical supervised adaptation for task-specific demands to decoding-time alignment for safety, finally leveraging human feedback and preference modeling to achieve sociolinguistic acuity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
