Year: 2023
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Elaraby, Mohamed, Lu, Mengyin, Dunn, Jacob, Zhang, Xueying, Wang, Yu, Liu, Shizhu, Tian, Pingchuan, Wang, Yuping, Wang, Yuxuan
Institution: University of Pittsburgh
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4386184855