发表机构
Indian Institute of Technology, Kharagpur（印度理工学院卡拉格普尔分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本论文提出“负责任智能”框架，通过主动学习与图知识减少幻觉、解码时对齐阻止有害生成及语言特定引导确保文化安全，为构建情境化、伦理化且文化适应的下一代AI提供蓝图。
AI 中文摘要
本论文提出了一个“负责任智能”框架，以应对人工智能在安全、伦理和文化敏感性方面的关键挑战。该框架推进了三个核心领域：首先，通过主动学习和基于图的知识来改进专业领域的领域自适应，以减少幻觉。其次，通过一种新颖的解码时对齐机制增强伦理严谨性，该机制能够实时主动阻止有害文本的生成。最后，通过语言特定的引导确保文化和多语言安全，尊重多样化的语言和社会规范。最终，这项工作为构建具备情境知识、伦理健全和文化适应性的下一代人工智能提供了蓝图。
英文摘要
This thesis proposes a framework for "responsible intelligence" to address AI's critical challenges in safety, ethics, and cultural sensitivity. It advances three core areas: First, it improves domain adaptation in specialized fields using active learning and graph-based knowledge to reduce hallucinations. Second, it enhances ethical rigor via a novel decoding-time alignment mechanism that proactively blocks harmful text generation in real-time. Finally, it ensures cultural and multilingual safety through language-specific steering that respects diverse linguistic and social norms. Ultimately, this work provides a blueprint for building next-generation AI that is contextually knowledgeable, ethically sound, and culturally adaptable.
CommentsThis is a preprint of a PhD thesis submitted to IIT KGP. The final, official version of record is available through the university's institutional repository
