Investigating the Influence of Prompt and Response Languages on LLM Content Generation

The paper investigates how the language of prompts and responses affects large language model (LLM) outputs. Using five models and 68 non‑translation questions, the authors compare English‑to‑English, English‑to‑Norwegian, Norwegian‑to‑Norwegian, and Norwegian‑to‑English conditions, yielding 1,348 responses after filtering. They find that prompt language strongly influences response length—Norwegian prompts shorten English outputs by ~37 % and English prompts shorten Norwegian outputs by ~41 %—while semantic similarity remains high across conditions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• nlp