HackerPapers

arXiv:2402.14531cs.CL

Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance

Ziqi Yin, Hao Wang, Kaito Horio, Daisuke Kawahara, Satoshi Sekine

Abstract

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.

arXiv comments
SICon 2024
Journal reference
DOI
Subjects
cs.CLComputation and Language

On Hacker News

Linked by 6 identifiable commenters in 6 comments across 6 threads, from Mar 2024 to Oct 2026. Found in 3 HN submissions from Feb 2024 to Apr 2025. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments6 threads

  1. Anthropic asks users to stop being mean to Claude 1 comment

    • Yes, I found the paper for you: • https://arxiv.org/abs/2510.04950 — Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy • https://arxiv.org/abs/2402.14531 — Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM…

      guessmynameView on HNParent context

  2. Caveman: Why use many token when few token do trick 1 comment

    • Politeness have impact (https://arxiv.org/abs/2402.14531) so I wouldn't be too fast to make any kind of claim with a technology we don't know exactly how it works.

      gchamonliveView on HNParent context

  3. AI is not a coworker, it's an exoskeleton 1 comment

    • And just like a real employee, this makes it work worse. (Old study, I wonder if it holds up on newer models? https://arxiv.org/pdf/2402.14531)

      ben_wView on HNParent context

  4. Qwen3-VL 1 comment

    • Depends on the model, but e.g. [1] found many models perform better if you are more polite. Though interestingly being rude can also sometimes improve performance at the cost of higher bias Intuitively it makes sense. The best sources tend to be either of moderately high…

      wongarsuView on HNParent context

  5. A staff engineer's journey with Claude Code 1 comment

    • Good creators tend to treat their tools with respect, and I can't imagine any reason we shouldn't feel gratitude toward our tools after a particularly satisfying session. Also, there may be selfish reasons to do this as well: (1) "Should We Respect LLMs? A Cross-Lingual Study on…

      CharlesWView on HNParent context

  6. The language you speak changes your perception of time 1 comment

    • Basically always worse in languages other than English. Not sure if it's just from volume of dataset or if it has to do with dataset quality, or the GPT architecture is inherently English-centric, but LLMs don't have like, a universal subconscious with superficial English…

      numpad0View on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.