English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As Large Language Models (LLMs) have advanced, they have brought forth newchallenges, with one of the prominent issues being LLM hallucination. Whilevarious mitigation techniques are emerging to address hallucination, it isequally crucial to delve into its underlying causes. Consequently, in thispreliminary exploratory investigation, we examine how linguistic factors inprompts, specifically readability, formality, and concreteness, influence theoccurrence of hallucinations. Our experimental results suggest that promptscharacterized by greater formality and concreteness tend to result in reducedhallucination. However, the outcomes pertaining to readability are somewhatinconclusive, showing a mixed pattern.

Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concreteness