# From Bytes to Biases: Investigating the Cultural Self-Perception of Large Language Models

arXiv: https://arxiv.org/abs/2312.17256 · HTML: https://mlsanity.com/paper/2312.17256/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 128 references that are in the map.
- First posted on arXiv 21 Dec 2023.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)
- [Long Short-Term Memory-Networks for Machine Reading](https://mlsanity.com/paper/1601.06733/) (2016)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models](https://mlsanity.com/paper/2304.03738/) (2023)
- [A Survey Of Cross-lingual Word Embedding Models](https://mlsanity.com/paper/1706.04902/) (2017)
- [Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions](https://mlsanity.com/paper/2309.12342/) (2023)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [The Self-Perception and Political Biases of ChatGPT](https://mlsanity.com/paper/2304.07333/) (2023)
- [In conversation with Artificial Intelligence: aligning language models with human values](https://mlsanity.com/paper/2209.00731/) (2022)
- [Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias](https://mlsanity.com/paper/2212.11261/) (2022)
- [Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5](https://mlsanity.com/paper/2305.04400/) (2023)
- [Large Language Models and the Reverse Turing Test](https://mlsanity.com/paper/2207.14382/) (2022)

## Built on by (most cited first, 1 of 1)

- [Surveying Attitudinal Alignment Between Large Language Models Vs. Humans Towards 17 Sustainable Development Goals](https://mlsanity.com/paper/2404.13885/) (2024)

## Abstract (arXiv)

Large language models (LLMs) are able to engage in natural-sounding conversations with humans, showcasing unprecedented capabilities for information retrieval and automated decision support. They have disrupted human-technology interaction and the way businesses operate. However, technologies based on generative artificial intelligence (GenAI) are known to hallucinate, misinform, and display biases introduced by the massive datasets on which they are trained. Existing research indicates that humans may unconsciously internalize these biases, which can persist even after they stop using the programs. This study explores the cultural self-perception of LLMs by prompting ChatGPT (OpenAI) and Bard (Google) with value questions derived from the GLOBE project. The findings reveal that their cultural self-perception is most closely aligned with the values of English-speaking countries and countries characterized by sustained economic competitiveness. Recognizing the cultural biases of LLMs and understanding how they work is crucial for all members of society because one does not want the black box of artificial intelligence to perpetuate bias in humans, who might, in turn, inadvertently create and train even more biased algorithms.