# CoCoA: Context-Conditional Cultural Alignment for Large Language Models

arXiv: https://arxiv.org/abs/2608.29492 · HTML: https://mlsanity.com/paper/2608.29492/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 24 of 24)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions](https://mlsanity.com/paper/2309.12342/) (2023)
- [CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies](https://mlsanity.com/paper/2404.15238/) (2024)
- [CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting](https://mlsanity.com/paper/2404.10199/) (2024)
- [Log Probabilities Are a Reliable Estimate of Semantic Plausibility in Base and Instruction-Tuned Language Models](https://mlsanity.com/paper/2403.14859/) (2024)
- [BiasEdit: Debiasing Stereotyped Language Models via Model Editing](https://mlsanity.com/paper/2503.08588/) (2025)
- [Commonsense Reasoning in Arab Culture](https://mlsanity.com/paper/2502.12788/) (2025)
- [CARE: Multilingual Human Preference Learning for Cultural Awareness](https://mlsanity.com/paper/2504.05154/) (2025)
- [CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis](https://mlsanity.com/paper/2505.19484/) (2025)
- [Mitigating Biases in Language Models via Bias Unlearning](https://mlsanity.com/paper/2509.25673/) (2025)
- [Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset](https://mlsanity.com/paper/2509.24468/) (2025)
- [CALM: Culturally Self-Aware Language Models](https://mlsanity.com/paper/2601.03483/) (2026)
- [Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations](https://mlsanity.com/paper/2604.03493/) (2026)
- [Learning to Route Languages for Multilingual Policy Optimization](https://mlsanity.com/paper/2605.25360/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often favor Western-associated entities across cultural contexts. Conventional debiasing methods aim for uniform neutrality, but cultural bias mitigation demands context-conditional behavior, preferring culturally appropriate entities when cultural cues are present and remaining neutral when they are absent. We propose CoCoA (Context-Conditional Cultural Alignment), a framework that learns this behavior through dual-context training on the same entity pairs under contexts with and without cultural cues. CoCoA combines a contrastive alignment objective with calibration and drift regularization, optimized through goal-aware gradient reconciliation. We evaluate CoCoA on CAMeL and Camellia, two entity-centric cultural bias benchmarks, across ten language settings and four LLMs. CoCoA reduces the Cultural Bias Score from 43 to 24 on average while maintaining near-neutral preferences at 50.2, with minimal impact on general performance across five standard benchmarks. These findings highlight that effective cultural alignment requires context-conditional modeling rather than uniform debiasing, and establish a new direction for mitigating entity-centric cultural bias in LLMs.