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.
arXiv:2609.36214v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used by people whose first language is not English, yet these users have been shown to receive systematic...
The study investigates how different prompt components affect language model responses in psychometric tests. By crossing five distinct baseline personas with five variants of each prompt element—persona wording, task instruction, item wording, and option symbol—the authors measure response shifts using the 1‑Wasserstein distance. Their analysis of 13 small open‑weight language models on the Big Five Inventory and Short Dark Triad reveals that task instruction and option symbol changes often cause more variation than paraphrasing the persona or item, with prompt artifacts explaining over 50% of the variation for many items.
arXiv:2610.02926v1 Announce Type: new Abstract: Standard factual benchmarks assume clean monolingual prompts and exact-match scoring, two assumptions that break simultaneously in real-world multiling...
Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavior has been widely studied for general text generation, its impact on code generation quality and programming conventions remains largely unexplored.
arXiv:2607. 14816v1 Announce Type: cross Abstract: Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias.
arXiv:2607. 13568v1 Announce Type: cross Abstract: Can a language model estimate its familiarity with an entity before generating an answer?
SWORD is a new benchmark that tests large language models’ ability to reject factually incorrect statements across eight major languages by distorting Wikidata triples. The benchmark reveals that models often perform better on semantically plausible distortions than on random ones, indicating a reliance on distributional familiarity rather than true factual verification. It also shows significant performance drops for East Asian languages, with gaps up to 28 percentage points, highlighting asymmetric multilingual factual reasoning capabilities.
arXiv:2603.12050v3 Announce Type: replace Abstract: Translated texts exhibit systematic differences from comparable texts originally written in the target language. Explaining this phenomenon, common...
arXiv:2512. 20757v2 Announce Type: replace-cross Abstract: Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs).
The paper proposes the interlingua hypothesis, suggesting that large language models translate by encoding a source sentence into a latent, task‑agnostic feature space and then decoding a target sentence from that space. Three lines of evidence support this: (1) BLEU variance across language pairs is largely explained by language‑specific competences without pair‑specific interactions; (2) many model components influence both monolingual and translation tasks; and (3) fine‑tuning on monolingual data recovers most translation gains seen with aligned documents. These findings converge to support the hypothesis and point toward new ways to understand and improve LLM translation.
arXiv:2607. 06327v1 Announce Type: cross Abstract: Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English.
The paper investigates how to fairly compare language models across languages, noting that current evaluation methods vary widely and lack empirical validation. By training controlled monolingual models on parallel data and testing multilingual LLMs, the authors find that many normalized metrics suffer from biases due to tokenization, encoding, and orthographic differences. Instead, they recommend using sentence‑level negative log‑likelihood over semantically equivalent sequences for more reliable cross‑lingual comparisons.