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：大语言模型（LLMs）彻底改变了自然语言处理（NLP）。尽管开源LLMs因参数量较少而对研究和实际应用十分便捷，但与更大规模的模型相比，它们往往存在更严重的幻觉问题。本文聚焦于测量并减少BLOOM 7B中的幻觉——该模型是此类公开可用于研究与商业应用的较弱开源LLMs的代表。我们提出HaloCheck，一个轻量级无知识黑盒框架，用于量化LLMs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LLMs中的幻觉问题。实验有效证明了这些LLMs在困难领域中的幻觉减少效果。