Tutoring Large Language Models to be Domain-adaptive, Precise and Safe

Abstract: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.

This 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

Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Computation and Language (cs.CL)

arXiv:2609.23071 [cs.AI]

(or arXiv:2609.23071v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.23071 arXiv-issued DOI via DataCite (pending registration)