mlsanityData to 14 Oct 2026

Personas Differ from Native-Language Generation: Language Pathways Shape LLM Interpersonal Advice

arXiv 2608.30873 ↗First posted 31 Aug 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

LLMs are increasingly used for interpersonal advice and as tools for studying social behavior across languages and cultures. A common shortcut for eliciting language- or culture-related variation is to ask a model to answer as a native speaker. We test whether this native-speaker persona reproduces the outputs obtained when models instead generate advice in the target language and translate the response back into English. Using 600 interpersonal advice questions across 13 languages and eight LLMs, we compare native-language generation followed by translation (NL) with native-speaker persona prompting (NP), measuring linguistic style, behavioral scaffolding, and forced-choice action recommendations. We find that NP and NL are not interchangeable. Compared to NL, NP often increases lexical social cues, including affiliation and positive tone, while reducing qualities such as concreteness and social attunement; NP also provides less actionable scaffolding in open-ended advice. In forced-choice scenarios, NP changes which action the model selects, favoring confrontation over redirection, with effect sizes varying across languages, topics, and models. Our results show that cross-lingual elicitation strategy is a consequential methodological choice that can change both how advice is framed and which actions models recommend.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 44 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

17 of 44 references.

References · 17

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  3. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  4. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  5. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  6. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 742
  7. 2023MEGA: Multilingual Evaluation of Generative AIcited by 293
  8. 2023ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learningcited by 206
  9. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  10. 2022"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Datasetcited by 162
  11. 2025Multilingual Prompting for Improving LLM Generation Diversitycited by 25
  12. 2023Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scalecited by 24
5 more
  1. 2024Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personascited by 23
  2. 2025LLMs and Cultural Values: the Impact of Prompt Language and Explicit Cultural Framingcited by 17
  3. 2024Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflictscited by 15
  4. 2025Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivitycited by 5
  5. 2026Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patternscited by 3

Built on by

Not cited yet.