# Localized Cultural Knowledge is Conserved and Controllable in Large Language Models

arXiv: https://arxiv.org/abs/2504.10191 · HTML: https://mlsanity.com/paper/2504.10191/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 63 of its 78 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 30 of 63)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning](https://mlsanity.com/paper/2005.00333/) (2020)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://mlsanity.com/paper/2412.03304/) (2024)
- [Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.16039/) (2023)
- [Lessons from the Trenches on Reproducible Evaluation of Language Models](https://mlsanity.com/paper/2405.14782/) (2024)
- [Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning](https://mlsanity.com/paper/2402.06619/) (2024)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models](https://mlsanity.com/paper/2102.00894/) (2021)

## Built on by (most cited first, 20 of 20)

- [Computational Hermeneutics: Evaluating generative AI as a cultural technology](https://mlsanity.com/paper/2604.16403/) (2026)
- [Rethinking Cross-lingual Alignment: Balancing Transfer and Cultural Erasure in Multilingual LLMs](https://mlsanity.com/paper/2510.26024/) (2025)
- [Social physics in the age of artificial intelligence](https://mlsanity.com/paper/2603.16900/) (2026)
- [Steering LLMs for Culturally Localized Generation](https://mlsanity.com/paper/2603.23301/) (2026)
- [Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs](https://mlsanity.com/paper/2604.19292/) (2026)
- [Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding](https://mlsanity.com/paper/2601.06403/) (2026)
- [Reflections and New Directions for Human-Centered Large Language Models](https://mlsanity.com/paper/2605.06901/) (2026)
- [Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version](https://mlsanity.com/paper/2606.11399/) (2026)
- [Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation](https://mlsanity.com/paper/2605.12515/) (2026)
- [Dissecting Physics Reasoning in Small Language Models: A Multi-Dimensional Analysis from an Educational Perspective](https://mlsanity.com/paper/2505.20707/) (2025)
- [AnnoSense: A Framework for Physiological Emotion Data Collection in Everyday Settings for AI](https://mlsanity.com/paper/2508.02680/) (2025)
- [Cultural Alien Sampler: Open-ended art generation balancing originality and coherence](https://mlsanity.com/paper/2510.20849/) (2025)
- [Benchmarking Concept-Spilling Across Languages in LLMs](https://mlsanity.com/paper/2601.12549/) (2026)
- [Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling](https://mlsanity.com/paper/2602.10732/) (2026)
- [HiMed: Incentivizing Hindi Reasoning in Medical LLMs](https://mlsanity.com/paper/2605.24635/) (2026)
- [Cultural Binding Heads in Language Models](https://mlsanity.com/paper/2605.28543/) (2026)
- [Where did the ambiguity go? Examining how multimodal models interpret polysemous words](https://mlsanity.com/paper/2608.00410/) (2026)
- [Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking](https://mlsanity.com/paper/2609.10745/) (2026)
- [The House with a Million Windows: Interactive Fiction for Narrative Restorying](https://mlsanity.com/paper/2609.12537/) (2026)
- [Geometric Representations of African Languages: A Regional Semantic Hub and Cultural Steering](https://mlsanity.com/paper/2609.36205/) (2026)

## Abstract (arXiv)

Just as humans display language patterns influenced by their native tongue when speaking new languages, LLMs often default to English-centric responses even when generating in other languages. Nevertheless, we observe that local cultural information persists within the models and can be readily activated for cultural customization. We first demonstrate that explicitly providing cultural context in prompts significantly improves the models' ability to generate culturally localized responses. We term the disparity in model performance with versus without explicit cultural context the explicit-implicit localization gap, indicating that while cultural knowledge exists within LLMs, it may not naturally surface in multilingual interactions if cultural context is not explicitly provided. Despite the explicit prompting benefit, however, the answers reduce in diversity and tend toward stereotypes. Second, we identify an explicit cultural customization vector, conserved across all non-English languages we explore, which enables LLMs to be steered from the synthetic English cultural world-model toward each non-English cultural world. Steered responses retain the diversity of implicit prompting and reduce stereotypes to dramatically improve the potential for customization. We discuss the implications of explicit cultural customization for understanding the conservation of alternative cultural world models within LLMs, and their controllable utility for translation, cultural customization, and the possibility of making the explicit implicit through soft control for expanded LLM function and appeal.