Although people are impressed by the content generation skills of large language models, the use of LLMs, such as ChatGPT, is limited by the domain grounding of the content. The correctness and groundedness of the generated content need to be based on a verified context, 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 domains 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 hallucinations and 2) a dual-decoder model that fuses RAG context to guide the generation process.

翻译：尽管人们对大型语言模型的内容生成能力印象深刻，但以ChatGPT为代表的LLMs在实际应用中仍受限于内容的领域落地性。生成内容的正确性与可验证性需要建立在经过验证的上下文基础上，例如检索增强生成（RAG）的结果。将LLMs适配到定制化领域时，一个关键问题在于生成的响应往往不完整，或新增内容未经验证甚至可能出现幻觉。先前关于幻觉检测的研究多集中于评估指标，这类方法难以适应动态领域，且易受越狱等攻击手段的影响。本研究提出：1）一种后处理算法，利用RAG上下文中的知识三元组进行幻觉校正；2）一种融合RAG上下文以指导生成过程的双解码器模型。