Prompt Politeness Affects LLM Accuracy
A recent study investigates how the politeness of prompts affects the accuracy of large language models (LLMs). The research found that impolite prompts yielded higher accuracy compared to polite ones, challenging previous assumptions about tone and performance. This highlights the need for further exploration of the social dimensions in human-AI interactions.
- ▪The study created a dataset of 250 unique prompts with varying politeness levels.
- ▪Impolite prompts achieved an accuracy of 84.8%, while very polite prompts had an accuracy of 80.8%.
- ▪These findings suggest that newer LLMs may respond differently to tonal variations than previously thought.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,317 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2510.04950 |
| Publication time | Tue, 26 May 2026 07:43:22 +0000 |
| Retrieval time | 2026-05-26T07:57:47.283Z |
| Last seen | 2026-05-26T07:57:47.283Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | aHaDV9Z08M2P |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Computation and Language arXiv:2510.04950 (cs) [Submitted on 6 Oct 2025] Title:Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper) Authors:Om Dobariya, Akhil Kumar View a PDF of the paper titled Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper), by Om Dobariya and Akhil Kumar View PDF Abstract:The wording of natural language prompts has been shown to influence the performance of large language models (LLMs), yet the role of politeness and tone remains underexplored. In this study, we investigate how varying levels of prompt politeness affect model accuracy on multiple-choice questions.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
