"Sorry, Come Again?" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing

arXiv:2403.18976v1 Announce Type: new
Abstract: Hallucination has emerged as the most vulnerable aspect of contemporary Large Language Models (LLMs). In this paper, we introduce the Sorry, Come Again (SCA) prompting, aimed to avoid LLM hallucinations by enhancing comprehension through: (i) optimal paraphrasing and (ii) injecting [PAUSE] tokens to delay LLM generation. First, we provide an in-depth analysis of linguistic nuances: formality, readability, and concreteness of prompts for 21 LLMs, and elucidate how these nuances contribute to hallucinated generation. Prompts with …

abstract arxiv cs.ai cs.cl hallucination hallucinations language language models large language large language models llm llm hallucinations llms paper paraphrasing prompting through type vulnerable