Saved in:
Bibliographic Details
Main Authors: Yin, Ziqi, Wang, Hao, Horio, Kaito, Kawahara, Daisuke, Sekine, Satoshi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.14531
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917801562734592
author Yin, Ziqi
Wang, Hao
Horio, Kaito
Kawahara, Daisuke
Sekine, Satoshi
author_facet Yin, Ziqi
Wang, Hao
Horio, Kaito
Kawahara, Daisuke
Sekine, Satoshi
contents We investigate the impact of politeness levels in prompts on the performance of large language models (LLMs). Polite language in human communications often garners more compliance and effectiveness, while rudeness can cause aversion, impacting response quality. We consider that LLMs mirror human communication traits, suggesting they align with human cultural norms. We assess the impact of politeness in prompts on LLMs across English, Chinese, and Japanese tasks. We observed that impolite prompts often result in poor performance, but overly polite language does not guarantee better outcomes. The best politeness level is different according to the language. This phenomenon suggests that LLMs not only reflect human behavior but are also influenced by language, particularly in different cultural contexts. Our findings highlight the need to factor in politeness for cross-cultural natural language processing and LLM usage.
format Preprint
id arxiv_https___arxiv_org_abs_2402_14531
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance
Yin, Ziqi
Wang, Hao
Horio, Kaito
Kawahara, Daisuke
Sekine, Satoshi
Computation and Language
We investigate the impact of politeness levels in prompts on the performance of large language models (LLMs). Polite language in human communications often garners more compliance and effectiveness, while rudeness can cause aversion, impacting response quality. We consider that LLMs mirror human communication traits, suggesting they align with human cultural norms. We assess the impact of politeness in prompts on LLMs across English, Chinese, and Japanese tasks. We observed that impolite prompts often result in poor performance, but overly polite language does not guarantee better outcomes. The best politeness level is different according to the language. This phenomenon suggests that LLMs not only reflect human behavior but are also influenced by language, particularly in different cultural contexts. Our findings highlight the need to factor in politeness for cross-cultural natural language processing and LLM usage.
title Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance
topic Computation and Language
url https://arxiv.org/abs/2402.14531