Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders

Jaya Krishna Mandivarapu, Xiaofeng Zhu

Abstract:

Although people are impressed by content generation skills of large language models, the
use of LLMs, such as ChatGPT, is limited by
the domain grounding of the content. The cor
rectness and groundedness of the generated
content need to be based on a verified con
text, such as results from Retrieval-Augmented
Generation (RAG). One important issue when
adapting LLMs to a customized domain is that
the generated responses are often incomplete,
or the additions are not verified and may even
be hallucinated. Prior studies on hallucination
detection have focused on evaluation metrics,
which are not easily adaptable to dynamic do
mains and can be vulnerable to attacks like jail
breaking. In this work, we propose 1) a post
processing algorithm that leverages knowledge
triplets in RAG context to correct hallucina
tions and 2) a dual-decoder model that fuses
RAGcontext to guide the generation process.