hofstede-s-vsm13-survey-most-eight-current-chat-models CLM-0305On Hofstede's VSM13 survey, most of eight current chat models answer closest to the United States when no culture is specified; a system prompt naming a target country moves seven of the eight toward that country's profile, with the largest gains for the countries furthest away at baseline (Japan and China, roughly 17-19% closer), yet those two remain the hardest to match even for the DeepSeek models.
Capability: Handling culture-specific norms and viewpoints
Observed on
DeepSeek-V3/V3.1, GPT-5, GPT-4.1, GPT-4, Claude Opus 4, Llama 3.1, Mistral Large, late 2025; six target countries; distance on Hofstede dimensions..
Model cards: GPT-4
Sources
- Validated by: Hofstede-dimension distance before and after prompting for six countries across eight models; seven of eight moved closer, gains 11-22% by country, Japan and China least matched.. One survey instrument and self-report style questions; Hofstede dimensions are contested as a measure of culture, so this measures alignment to a questionnaire profile rather than behaviour.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- When a scenario pits a stated personal preference against a local cultural norm, models' choice of norm over preference shifts more with the scenario's country (about 8 points) than with the user's age (1) or gender (under 1), instruction tuning shifts it non-uniformly, and while models can match the majority human choice per country they do not reproduce the spread of human answers, with best correlation to human response distributions only about 0.24.Handling culture-specific norms and viewpoints · reviewed by AI
- On multimodal cultural-interpretation multiple-choice questions, pipelines that pool several same-backbone evidence streams (perception, retrieval, web verification) and weight them by scored relevance beat majority voting, self-consistency and agent debate mainly on the items where the streams disagree, and the margin shrinks sharply as the backbone gets stronger.Getting more from several models than from one · reviewed by AI
- When a document image states multi-step selection constraints in narrative text and the supporting numbers sit in several charts, multimodal models degrade steadily as either the number of logical hops (2 to 5) or the number of charts (2 to 6) grows, with the best model reaching 62.83% overall against over 90% for human annotators.Carrying a chain of inference through to its conclusion · reviewed by AI
- At inference time and with no weights, data or internals, instantiating a country as a panel of four World-Values-Survey-grounded personas and using their disagreement, not their consensus, as the steering signal reduced cultural misalignment on Moral-Machine-style dilemmas (MultiTP) by 10-24% across 20 countries and seven open backbones from 2B to 70B.Handling culture-specific norms and viewpoints · reviewed by AI
- On multi-session dialogue questions whose answers depend only on how an utterance was delivered, a cascaded ASR-then-LLM pipeline (Whisper large-v3 into a frontier model) scores below 7B audio-native models on the same clips, and below even a transcript-only baseline, because the transcription step drops delivery cues entirely and adds content errors.Understanding speech and audio · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: A survey instrument other than VSM13 on which the default profile is not US-like, or cultural prompting that moves models away from the target on held-out items.