Halo：开源弱大型语言模型中幻觉的估计与减少
Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models
AI总结：
本文针对开源弱大型语言模型（如BLOOM 7B）的幻觉问题，提出HaloCheck框架量化幻觉严重程度，并通过知识注入和师生方法减少幻觉，实验证明其有效性。
摘要：
大型语言模型（LLMs）彻底改变了自然语言处理（NLP）。尽管开源LLMs便于研究和实际应用，但参数较少的开源LLMs往往比其更大的同类模型遭受更严重的幻觉。本文专注于测量和减少BLOOM 7B中的幻觉，BLOOM 7B是此类较弱的、可用于研究和商业应用的开源LLMs的代表。我们引入了HaloCheck，这是一个轻量级的黑盒无知识框架，旨在量化LLMs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LLMs中的幻觉。我们的实验有效地证明了在这些LLMs的挑战性领域中幻觉的减少。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
