# Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models

arXiv: https://arxiv.org/abs/2606.07877 · HTML: https://mlsanity.com/paper/2606.07877/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 60 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 28 of 28)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [Survey of Cultural Awareness in Language Models: Text and Beyond](https://mlsanity.com/paper/2411.00860/) (2024)
- [Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking](https://mlsanity.com/paper/2402.09369/) (2024)
- [A Survey of Uncertainty Estimation Methods on Large Language Models](https://mlsanity.com/paper/2503.00172/) (2025)
- [Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias](https://mlsanity.com/paper/2308.00225/) (2023)
- [Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions](https://mlsanity.com/paper/2410.02584/) (2024)
- [A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications](https://mlsanity.com/paper/2503.17003/) (2025)
- [Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution](https://mlsanity.com/paper/2403.03121/) (2024)
- [Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language](https://mlsanity.com/paper/2406.17753/) (2024)
- [CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming](https://mlsanity.com/paper/2410.02677/) (2024)
- [Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models](https://mlsanity.com/paper/2412.18863/) (2024)
- [Mind the (Belief) Gap: Group Identity in the World of LLMs](https://mlsanity.com/paper/2503.02016/) (2025)
- [Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactions](https://mlsanity.com/paper/2503.02038/) (2025)
- [Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment](https://mlsanity.com/paper/2504.12663/) (2025)
- [Towards Region-aware Bias Evaluation Metrics](https://mlsanity.com/paper/2406.16152/) (2024)
- [Exploring Cultural Variations in Moral Judgments with Large Language Models](https://mlsanity.com/paper/2506.12433/) (2025)
- [GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences](https://mlsanity.com/paper/2510.11952/) (2025)
- [What Did They Mean? How LLMs Resolve Ambiguous Social Situations across Perspectives and Roles](https://mlsanity.com/paper/2604.23942/) (2026)

## Abstract (arXiv)

Large language models are increasingly used for social decision-making situations that require balancing cultural norms with personal preferences. For example, a user preferring honesty might ask whether to correct a coworker publicly when local norms favor indirect feedback. Yet existing research studies cultural alignment and personalization largely separately. We introduce PACT, the Personal-Preference and Cultural-Norm Trade-off framework, which evaluates whether models choose to follow a cultural norm or allow personal preferences. We find that LLMs vary in how rigidly they enforce cultural norms, with behavior shifted more by country context (7.8%) than age (1%) and gender (0.7%) and shifting non-uniformly after instruction tuning. Furthermore, our five-country human study on PACT shows that culture-following in humans is mainly driven by scenario country, with the lowest agreement when participants judge their own cultural contexts, showing within-culture pluralism. Finally, human-LLM alignment experiments show that models can match majority choices, but fail to capture response distributions and uncertainty (with best correlations reaching only 0.24). Together, these findings motivate alignment evaluations that go beyond majority to capture cultural pluralism and disagreement in social judgment.