# LLMs Infer Cultural Context but Fail to Apply It When Responding

arXiv: https://arxiv.org/abs/2606.17688 · HTML: https://mlsanity.com/paper/2606.17688/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens](https://mlsanity.com/paper/2401.17377/) (2024)
- [A fine-grained comparison of pragmatic language understanding in humans and language models](https://mlsanity.com/paper/2212.06801/) (2022)
- [Reasoning About Pragmatics with Neural Listeners and Speakers](https://mlsanity.com/paper/1604.00562/) (2016)
- [WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models](https://mlsanity.com/paper/2404.16308/) (2024)
- [The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs](https://mlsanity.com/paper/2210.14986/) (2022)
- [Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations](https://mlsanity.com/paper/2502.07068/) (2025)
- [NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models](https://mlsanity.com/paper/2404.12464/) (2024)
- [Grounding 'Grounding' in NLP](https://mlsanity.com/paper/2106.02192/) (2021)
- [Stereotype or Personalization? User Identity Biases Chatbot Recommendations](https://mlsanity.com/paper/2410.05613/) (2024)
- [Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs](https://mlsanity.com/paper/2502.08045/) (2025)
- [Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys](https://mlsanity.com/paper/2401.10352/) (2024)
- [Pragmatic Issue-Sensitive Image Captioning](https://mlsanity.com/paper/2004.14451/) (2020)
- [CULEMO: Cultural Lenses on Emotion -- Benchmarking LLMs for Cross-Cultural Emotion Understanding](https://mlsanity.com/paper/2503.10688/) (2025)
- [Where's My Head? Definition, Dataset and Models for Numeric Fused-Heads Identification and Resolution](https://mlsanity.com/paper/1905.10886/) (2019)
- [Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors](https://mlsanity.com/paper/2506.06987/) (2025)
- [Pragmatic Reasoning improves LLM Code Generation](https://mlsanity.com/paper/2502.15835/) (2025)
- [Scalar Adjective Identification and Multilingual Ranking](https://mlsanity.com/paper/2105.01180/) (2021)
- [Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4](https://mlsanity.com/paper/2505.18322/) (2025)
- [VAQUUM: Are Vague Quantifiers Grounded in Visual Data?](https://mlsanity.com/paper/2502.11874/) (2025)
- [Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs](https://mlsanity.com/paper/2604.19292/) (2026)
- [Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog](https://mlsanity.com/paper/2507.14063/) (2025)
- [How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models](https://mlsanity.com/paper/2604.15873/) (2026)

## Abstract (arXiv)

Recent work has shown that LLMs overrepresent dominant cultures, particularly Western ones, while marginalizing others. We investigate whether this affects models' ability to generate culturally adapted responses by evaluating their use of local measurement units based on the user's perceived cultural background. We introduce Cultural and Pragmatic Response Inference (CAPRI), a dataset of conversations with varying levels of cultural cues. Experiments with state-of-the-art LLMs show that models can infer cultural background and recall relevant conventions, but often fail to utilize the information to adapt their answers to the relevant cultural conventions, unless explicitly prompted to perform the tasks sequentially. We further evaluate adaptation to the interpretation of time and quantity expressions, two subjective language grounding dimensions that are affected by culture. We find that models increasingly adapt their answers as cultural cues accumulate, but their priors are not culture-neutral, sometimes aligning with the model's country of origin. Overall, CAPRI provides a resource for future research aimed at narrowing the gap between cultural knowledge and culturally adaptive language generation.