cultural-competence CAP-0007 · activeHandling culture-specific norms and viewpoints
Covers implicit cultural norms, dialects, local pragmatics, and representing the spread of a population's views; excludes general multilingual fluency or factual trivia about cultures.
Tags: general
Proposed from the ingestion pipeline rather than chosen by hand. 5 papers independently pointed at this same competence, arriving under 5 different names (cultural-perspective- diversity, dialect-cultural-competence, cultural-competence, cultural- knowledge, cultural-alignment-transfer), which is the signal that it is a real recurring topic and not one author's framing. Five separate proposals describe the same competence, making it clearly recurring rather than a one-off framing.
What counts as this capability
Scope boundary used when deciding whether a paper is really about this capability, rather than merely mentioning it.
Covers implicit cultural norms, dialects, local pragmatics, and representing the spread of a population's views; excludes general multilingual fluency or factual trivia about cultures.
Claims
- observationsingle paper↑1↓0On expert-authored Saudi-dialect prompts scored against rubric criteria derived from expert ground truths, four frontier models all score under 55% and their dominant failure is distorting register and flattening pragmatic nuance (37.3% of 466 errors) rather than stating falsehoods (11.2%), so MSA-fluent models are not dialectally competent.
- mechanismsingle paper↑1↓0Fine-tuning for cultural alignment scores raises agreement with a country's majority answers on the World Values Survey while collapsing the spread of answers: tuned models anchor to the plurality option (a 39% human share in the example) and cover less than half of the human response dimensions, dropping to a quarter for one model, so alignment gains partly measure flattening rather than cultural understanding.
- observationsingle paper↑1↓0On 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.
- observationsingle paper↑1↓0At 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.
- observationsingle paper↑1↓0When 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.
Techniques
- Cultural prompting via a country-naming system promptpromptingState the target country in the system prompt so the model answers survey-style questions as a member of that culture; measured as reduced distance to the country's Hofstede profile.
- Persona-disagreement steering for cultural alignmentpromptingPrompt several demographically distinct personas grounded in a country's survey data, treat their agreement as already calibrated and their disagreement as the correction signal, and combine their answers to shift the base model's output to
Sources
Every paper, post or observation behind this capability. Ones cited by a claim show the claim and its stance; ones filed directly are about the capability but have no claim drafted from them yet. Open one to add support or contest it.
- Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs2026-09-01↑ supports a claim here
- ↑ supports a claim here
- about this capability · no claim drafted yet
- ↑ supports a claim here
- ↑ supports a claim here
- ↑ supports a claim here
Capabilities are a way of carving up the subject, and carvings are arguable. Say so if this one is wrong — especially a proposed one, which a pipeline added because several papers used the same framing, not because anyone decided it was right.