Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concreteness
This work addresses the problem of LLM hallucinations for users and developers, but it is incremental as it explores specific linguistic factors without introducing new mitigation methods.
The paper investigates how linguistic features in prompts—readability, formality, and concreteness—affect hallucinations in Large Language Models, finding that more formal and concrete prompts reduce hallucinations, while readability results are mixed.
As Large Language Models (LLMs) have advanced, they have brought forth new challenges, with one of the prominent issues being LLM hallucination. While various mitigation techniques are emerging to address hallucination, it is equally crucial to delve into its underlying causes. Consequently, in this preliminary exploratory investigation, we examine how linguistic factors in prompts, specifically readability, formality, and concreteness, influence the occurrence of hallucinations. Our experimental results suggest that prompts characterized by greater formality and concreteness tend to result in reduced hallucination. However, the outcomes pertaining to readability are somewhat inconclusive, showing a mixed pattern.