mlsanityData to 14 Oct 2026

Large Language Models as Superpositions of Cultural Perspectives

arXiv 2307.07870 ↗First posted 15 Jul 2023cs.CL cs.AI cs.LGcited by 49

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) are often misleadingly recognized as having a personality or a set of values. We argue that an LLM can be seen as a superposition of perspectives with different values and personality traits. LLMs exhibit context-dependent values and personality traits that change based on the induced perspective (as opposed to humans, who tend to have more coherent values and personality traits across contexts). We introduce the concept of perspective controllability, which refers to a model's affordance to adopt various perspectives with differing values and personality traits. In our experiments, we use questionnaires from psychology (PVQ, VSM, IPIP) to study how exhibited values and personality traits change based on different perspectives. Through qualitative experiments, we show that LLMs express different values when those are (implicitly or explicitly) implied in the prompt, and that LLMs express different values even when those are not obviously implied (demonstrating their context-dependent nature). We then conduct quantitative experiments to study the controllability of different models (GPT-4, GPT-3.5, OpenAssistant, StableVicuna, StableLM), the effectiveness of various methods for inducing perspectives, and the smoothness of the models' drivability. We conclude by examining the broader implications of our work and outline a variety of associated scientific questions. The project website is available at https://sites.google.com/view/llm-superpositions .

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 19 of its 41 references that are in the map. First posted on arXiv 15 Jul 2023.

Builds on

19 of 41 references.

References · 19

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2017Deep reinforcement learning from human preferencescited by 3,912
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  7. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  8. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  9. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
  10. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 206
  11. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 155
  12. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 149
7 more
  1. 2023The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Datasetcited by 148
  2. 2022Language Models as Agent Modelscited by 132
  3. 2022Who is GPT-3? An Exploration of Personality, Values and Demographicscited by 112
  4. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  5. 2019SciPy 1.0--Fundamental Algorithms for Scientific Computing in Pythoncited by 49
  6. 2022Data Governance in the Age of Large-Scale Data-Driven Language Technologycited by 33
  7. 2021Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Modelscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 24; 2025: 14; 2026: 10.

49 papers.

Sort:

By area:

  1. 2023The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variantscited by 311
  2. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  3. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 167
  4. 2024Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learningcited by 81
  5. 2024Benchmarking Distributional Alignment of Large Language Modelscited by 61
  6. 2024PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferencescited by 54
  7. 2025Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactionscited by 52
  8. 2024CultureLLM: Incorporating Cultural Differences into Large Language Modelscited by 50
  9. 2024Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them incited by 46
  10. 2025Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation Historycited by 26
  11. 2024CulturePark: Boosting Cross-cultural Understanding in Large Language Modelscited by 24
  12. 2024Helpful assistant or fruitful facilitator? Investigating how personas affect language model behaviorcited by 21
37 more
  1. 2024The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Modelscited by 19
  2. 2024Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learningcited by 19
  3. 2024Multilingual Large Language Models: A Systematic Surveycited by 18
  4. 2024When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settingscited by 17
  5. 2024Do LLMs have Consistent Values?cited by 14
  6. 2024Measuring Human and AI Values Based on Generative Psychometrics with Large Language Modelscited by 13
  7. 2024Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Modelscited by 11
  8. 2024Cultural Value Differences of LLMs: Prompt, Language, and Model Sizecited by 10
  9. 2024Neuron-based Personality Trait Induction in Large Language Modelscited by 9
  10. 2025Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behaviorcited by 9
  11. 2024Large Language Models Can Infer Personality from Free-Form User Interactionscited by 8
  12. 2025Meta-Cultural Competence: Climbing the Right Hill of Cultural Awarenesscited by 8
  13. 2026Knowing But Not Doing: Convergent Morality and Divergent Action in LLMscited by 7
  14. 2025Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue Historycited by 5
  15. 2024Analyzing Nobel Prize Literature with Large Language Modelscited by 4
  16. 2024A dataset of questions on decision-theoretic reasoning in Newcomb-like problemscited by 4
  17. 2025Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditionscited by 4
  18. 2025Adversarial Attack on Large Language Models using Exponentiated Gradient Descentcited by 4
  19. 2025EtiCor++: Towards Understanding Etiquettical Bias in LLMscited by 3
  20. 2025Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal Closenesscited by 3
  21. 2024Exploring Cross-lingual Latent Transplantation: Mutual Opportunities and Open Challengescited by 2
  22. 2025Do Language Models Think Consistently? A Study of Value Preferences Across Varying Response Lengthscited by 2
  23. 2025User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMscited by 2
  24. 2026x1: Learning to Think Adaptively Across Languages and Culturescited by 2
  25. 2026LLMs Contain Multitudes: How Deployment Context Reshapes Model-Level Preferences and Valuescited by 2
  26. 2024The Elephant in the Room -- Why AI Safety Demands Diverse Teamscited by 1
  27. 2024Prompt and Prejudicecited by 1
  28. 2025Prompt Optimization Across Multiple Agents for Representing Diverse Human Populationscited by 1
  29. 2026DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mappingcited by 1
  30. 2026Differentially Private Preference Data Synthesis for Large Language Model Alignmentcited by 1
  31. 2025Designing LLMs for cultural sensitivity: Evidence from English-Japanese translationcited by 0
  32. 2025Effectiveness of Large Language Models in Simulating Regional Psychological Structures: An Empirical Examination of Personality and Subjective Well-beingcited by 0
  33. 2026PPCR-IM: A System for Multi-layer DAG-based Public Policy Consequence Reasoning and Social Indicator Mappingcited by 0
  34. 2026Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistencycited by 0
  35. 2026Anchoring LLM Gender Bias to Human Baselines: A Cross-Lingual Auditcited by 0
  36. 2026GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Modelscited by 0
  37. 2026Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models
  2. 2025Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?
  3. 2023Heterogeneous Value Alignment Evaluation for Large Language Models
  4. 2024Extroversion or Introversion? Controlling The Personality of Your Large Language Models
  5. 2026Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM Agents
  6. 2025From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers
  7. 2025Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models
  8. 2025Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait Alignment