mlsanityData to 7 Oct 2026

Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning

arXiv 2408.16482 ↗First posted 29 Aug 2024cs.CLcited by 18

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

Improving the alignment of Large Language Models (LLMs) with respect to the cultural values that they encode has become an increasingly important topic. In this work, we study whether we can exploit existing knowledge about cultural values at inference time to adjust model responses to cultural value probes. We present a simple and inexpensive method that uses a combination of in-context learning (ICL) and human survey data, and show that we can improve the alignment to cultural values across 5 models that include both English-centric and multilingual LLMs. Importantly, we show that our method could prove useful in test languages other than English and can improve alignment to the cultural values that correspond to a range of culturally diverse countries.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 31 of its 40 references that are in the map. First posted on arXiv 29 Aug 2024.

Builds on

31 of 40 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Aligning to Thousands of Preferences via System Message Generalization28 May
  2. 2023From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models23 Aug
  3. 2023Aligning Language Models to User Opinions24 May
  4. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback9 Mar

Other references · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  6. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  7. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  8. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  9. 2023Whose Opinions Do Language Models Reflect?cited by 759
  10. 2022A Survey on In-context Learningcited by 717
  11. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  12. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
15 more
  1. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervisioncited by 318
  2. 2023Large Language Model Alignment: A Surveycited by 241
  3. 2022Challenges and Strategies in Cross-Cultural NLPcited by 216
  4. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 204
  5. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 203
  6. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  7. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 166
  8. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 147
  9. 2023Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanationscited by 85
  10. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 82
  11. 2023Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Promptingcited by 80
  12. 2023Large Language Models as Superpositions of Cultural Perspectivescited by 48
  13. 2023Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?cited by 39
  14. 2024Whose Emotions and Moral Sentiments Do Language Models Reflect?cited by 20
  15. 2024The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuningcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 14; 2026: 3.

18 papers.

Sort:

By area:

  1. 2024Self-Pluralising Culture Alignment for Large Language Modelscited by 31
  2. 2025Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMscited by 26
  3. 2025Multiple LLM Agents Debate for Equitable Cultural Alignmentcited by 20
  4. 2025PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culturecited by 20
  5. 2025CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesiscited by 14
  6. 2025ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learningcited by 10
  7. 2025From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMscited by 9
  8. 2025An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritagecited by 8
  9. 2025CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimizationcited by 5
  10. 2025Uncovering Cultural Representation Disparities in Vision-Language Modelscited by 4
  11. 2025Evaluation of Cultural Competence of Vision-Language Modelscited by 3
  12. 2026Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoningcited by 3
6 more
  1. 2026Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Modelscited by 3
  2. 2025From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Testcited by 2
  3. 2025Improving the Distributional Alignment of LLMs using Supervisioncited by 2
  4. 2025Can Large Language Models Predict Associations Among Human Attitudes?cited by 1
  5. 2026DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mappingcited by 1
  6. 2025NurValues: Real-World Nursing Values Evaluation for Large Language Models in Clinical Contextcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs
  2. 2026Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency
  3. 2023CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models
  4. 2026AlignCultura: Towards Culturally Aligned Large Language Models?
  5. 2025Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
  6. 2026Progressing beyond Art Masterpieces or Touristic Clich'es: how to assess your LLMs for cultural alignment?
  7. 2026Understanding Cultural Alignment in Multilingual LLMs via Natural Debate Statements ↗
  8. 2025ALIGN: Word Association Learning for Cultural Alignment in Large Language Models