mlsanityData to 13 Oct 2026

Cultural Value Differences of LLMs: Prompt, Language, and Model Size

arXiv 2407.16891 ↗First posted 17 Jun 2024cs.CY cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Our study aims to identify behavior patterns in cultural values exhibited by large language models (LLMs). The studied variants include question ordering, prompting language, and model size. Our experiments reveal that each tested LLM can efficiently behave with different cultural values. More interestingly: (i) LLMs exhibit relatively consistent cultural values when presented with prompts in a single language. (ii) The prompting language e.g., Chinese or English, can influence the expression of cultural values. The same question can elicit divergent cultural values when the same LLM is queried in a different language. (iii) Differences in sizes of the same model (e.g., Llama2-7B vs 13B vs 70B) have a more significant impact on their demonstrated cultural values than model differences (e.g., Llama2 vs Mixtral). Our experiments reveal that query language and model size of LLM are the main factors resulting in cultural value differences.

Key facts. Cited by 10 papers in the map (data through 13 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

19 of 39 references.

References · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,320
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,979
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,876
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,831
  5. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,798
  6. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,053
  7. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,541
  8. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 690
  9. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 470
  10. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  11. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 260
  12. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 205
7 more
  1. 2021Societal Biases in Language Generation: Progress and Challengescited by 202
  2. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 147
  3. 2019Open Sesame: Getting Inside BERT's Linguistic Knowledgecited by 119
  4. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  5. 2023Large Language Models as Superpositions of Cultural Perspectivescited by 49
  6. 2023You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instrumentscited by 48
  7. 2022Downstream Datasets Make Surprisingly Good Pretraining Corporacited by 20

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 7; 2026: 3.

10 papers.

  1. 2025PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modelingcited by 4
  2. 2025Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Benchcited by 3
  3. 2025CCD-Bench: Probing Cultural Conflict in Large Language Model Decision-Makingcited by 3
  4. 2026Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Modelscited by 3
  5. 2025Reproducibility Study of "Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents"cited by 2
  6. 2025Cash or Comfort? How LLMs Value Your Inconveniencecited by 1
  7. 2025A Cross-Cultural Comparison of LLM-based Public Opinion Simulation: Evaluating Chinese and U.S. Models on Diverse Societiescited by 1
  8. 2026Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebookcited by 1
  9. 2025DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural promptingcited by 0
  10. 2026Beyond Surface Cues: Disentangling Sociocultural Signals in Multilingual LLMscited by 0