Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP). Although convenient for research and practical applications, open-source LLMs with fewer parameters often suffer from severe hallucinations compared to their larger counterparts. This paper focuses on measuring and reducing hallucinations in BLOOM 7B, a representative of such weaker open-source LLMs that are publicly available for research and commercial applications. We introduce HaloCheck, a lightweight BlackBox knowledge-free framework designed to quantify the severity of hallucinations in LLMs. Additionally, we explore techniques like knowledge injection and teacher-student approaches to alleviate hallucinations in low-parameter LLMs. Our experiments effectively demonstrate the reduction of hallucinations in challenging domains for these LLMs.

翻译：摘要：大型语言模型（LLMs）彻底改变了自然语言处理（NLP）领域。尽管参数较少的开源LLMs便于研究及实际应用，但与规模更大的同类模型相比，这类模型往往存在严重的幻觉问题。本文聚焦于测量并缓解BLOOM 7B这一典型弱开源LLM（可公开用于研究与商业应用）中的幻觉现象。我们提出HaloCheck——一种轻量级、无知识库的黑盒框架，用于量化LLM中幻觉的严重程度。此外，我们探索了知识注入与师生方法等技术，以缓解低参数LLM中的幻觉问题。实验有效证明了这些方法在具有挑战性的领域中对降低此类模型幻觉的成效。