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：大语言模型（LLMs）彻底改变了自然语言处理（NLP）。尽管对研究和实际应用而言十分便利，但参数较少的开源大语言模型相比其更大规模的同类模型，往往存在更严重的幻觉问题。本文聚焦于测量和减少BLOOM 7B（一种可供研究和商业应用的开源弱LLM代表）中的幻觉。我们提出HaloCheck，一种轻量级、黑箱且无需知识的框架，旨在量化LLM中幻觉的严重程度。此外，我们探索了知识注入和师生方法等技术，以缓解低参数LLM中的幻觉。我们的实验有效证明了这些LLM在挑战性领域中幻觉的减少。