70/100

Moderate evidence

GainPublished recordLifestyleGood Space

Prompting with Respect: Cultural Norms and User Experience in LLM Interactions

Truvace record
TRV-2026-2679raw data (JSON)
Version
v1Published
First published
Evidence type
Randomized controlled trial
Sources
1 sourcePeer-reviewed
sha256
272b0e1213cc…check it

Despite growing interest in prompt engineering, its influence on user experience-particularly in relation to cultural communication norms-remains largely unexplored. This controlled experiment examined how respectful versus directive prompting-a culturally meaningful contrast in Korean-affects Korean users' psychological experience during LLM interactions. Forty-three Korean female college students were randomly assigned to respectful prompt (RP) (using polite requests, compliments, and gratitude) or directive p…

The gain

In a randomized experiment with 43 Korean female college students, those who wrote polite, grateful prompts to ChatGPT reported significantly higher satisfaction, especially affinity and likability, than those who used imperatives and criticism.

What this doesn’t fix

The experiment involved only 43 Korean female college students on a single writing task, which limits how far the results extend to other groups, languages or tasks.

Sources

1 on file
  1. Peer-reviewed2026-09-11

Cite this record

v1

Truvace Impact Record TRV-2026-2679, v1: “Prompting with Respect: Cultural Norms and User Experience in LLM Interactions.” Truvace, 2026-11-12. /record/TRV-2026-2679 (accessed on the day you copy it). sha256 272b0e1213ccb111…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv1272b0e1213cc…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2679 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.