The Silent Curriculum: How Does LLM Monoculture Shape Educational Content and Its Accessibility?

• URL: http://arxiv.org/abs/2407.10371v1
• Date: Sat, 11 May 2024 12:02:44 GMT
• Title: The Silent Curriculum: How Does LLM Monoculture Shape Educational Content and Its Accessibility?
• Authors: Aman Priyanshu, Supriti Vijay,
• Abstract summary: Large Language Models (LLMs) offer information with unprecedented convenience compared to traditional search engines. We call this the "Silent Curriculum," where our focus shifts towards a particularly impressionable demographic: children. We unpack this concept through a short experiment navigating children's storytelling, occupational-ethnic biases, and self-diagnosed annotations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Large Language Models (LLMs) ascend in popularity, offering information with unprecedented convenience compared to traditional search engines, we delve into the intriguing possibility that a new, singular perspective is being propagated. We call this the "Silent Curriculum," where our focus shifts towards a particularly impressionable demographic: children, who are drawn to the ease and immediacy of acquiring knowledge through these digital oracles. In this exploration, we delve into the sociocultural ramifications of LLMs, which, through their nuanced responses, may be subtly etching their own stereotypes, an algorithmic or AI monoculture. We hypothesize that the convergence of pre-training data, fine-tuning datasets, and analogous guardrails across models may have birthed a distinct cultural lens. We unpack this concept through a short experiment navigating children's storytelling, occupational-ethnic biases, and self-diagnosed annotations, to find that there exists strong cosine similarity (0.87) of biases across these models, suggesting a similar perspective of ethnic stereotypes in occupations. This paper invites a reimagining of LLMs' societal role, especially as the new information gatekeepers, advocating for a paradigm shift towards diversity-rich landscapes over unintended monocultures.

Related papers

• Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples [13.476728526770023]
  A key challenge in measuring cultural biases is that determining which group an individual belongs to often depends upon cultural context cues in images.<n>We introduce Cultural Counterfactuals: a high-quality synthetic dataset containing nearly 60k counterfactual images for measuring cultural biases related to religion, nationality, and socioeconomic status.
  arXiv  Detail & Related papers  (2026-03-02T20:19:53Z)
• The Curious Case of Curiosity across Human Cultures and LLMs [45.37389175832353]
  We investigate cultural variation in curiosity using Yahoo! Answers, a real-world multi-country dataset spanning diverse topics.<n>We find that Large Language Models flatten cross-cultural diversity, aligning more closely with how curiosity is expressed in Western countries.<n>We then explore fine-tuning strategies to induce curiosity in LLMs, narrowing the human-model alignment gap by up to 50%.
  arXiv  Detail & Related papers  (2025-10-14T19:42:24Z)
• Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model's Empathy [1.6489674562395387]
  We investigate how Large Language Models' cognitive and affective empathy vary across user personas defined by intersecting demographic attributes.<n>Our study introduces a novel intersectional analysis spanning 315 unique personas, constructed from combinations of age, culture, and gender.<n>We show that they broadly reflect real-world empathetic trends, with notable misalignments for certain groups, such as those from Confucian culture.
  arXiv  Detail & Related papers  (2025-10-11T20:04:57Z)
• Which Cultural Lens Do Models Adopt? On Cultural Positioning Bias and Agentic Mitigation in LLMs [53.07843733899881]
  Large language models (LLMs) have unlocked a wide range of downstream generative applications.<n>We find that they also risk perpetuating subtle fairness issues tied to culture, positioning their generations from the perspectives of the mainstream US culture.<n>We propose 2 inference-time mitigation methods to resolve these biases.
  arXiv  Detail & Related papers  (2025-09-25T12:28:25Z)
• GPT and Prejudice: A Sparse Approach to Understanding Learned Representations in Large Language Models [0.0]
  Large language models (LLMs) are increasingly trained on massive, uncurated corpora.<n>We show that pairing LLMs with sparse autoencoders (SAEs) enables interpretation not only of model behavior but also of the deeper structures, themes, and biases embedded in the training data.<n>We train a GPT-style transformer model exclusively on the novels of Jane Austen, a corpus rich in social constructs and narrative patterns.
  arXiv  Detail & Related papers  (2025-09-24T11:10:16Z)
• From Word to World: Evaluate and Mitigate Culture Bias via Word Association Test [48.623761108859085]
  We extend the human-centered word association test (WAT) to assess the alignment of large language models with cross-cultural cognition.<n>To mitigate the culture preference, we propose CultureSteer, an innovative approach that integrates a culture-aware steering mechanism.
  arXiv  Detail & Related papers  (2025-05-24T07:05:10Z)
• From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs [57.43233760384488]
  Adapting cultural values in Large Language Models (LLMs) presents significant challenges.<n>Prior work primarily aligns LLMs with different cultural values using World Values Survey (WVS) data.<n>In this paper, we investigate WVS-based training for cultural value adaptation and find that relying solely on survey data cane cultural norms and interfere with factual knowledge.
  arXiv  Detail & Related papers  (2025-05-22T09:00:01Z)
• CARE: Aligning Language Models for Regional Cultural Awareness [28.676469530858924]
  Existing language models (LMs) often exhibit a Western-centric bias and struggle to represent diverse cultural knowledge. Previous attempts to address this rely on synthetic data and express cultural knowledge only in English. We first introduce CARE, a multilingual resource of 24.1k responses with human preferences on 2,580 questions about Chinese and Arab cultures.
  arXiv  Detail & Related papers  (2025-04-07T14:57:06Z)
• From Structured Prompts to Open Narratives: Measuring Gender Bias in LLMs Through Open-Ended Storytelling [2.4374097382908477]
  Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases. This study introduces a novel evaluation framework to uncover gender biases in LLMs, focusing on their occupational narratives.
  arXiv  Detail & Related papers  (2025-03-20T07:15:45Z)
• Meta-Cultural Competence: Climbing the Right Hill of Cultural Awareness [11.98067475490853]
  We argue that it is not cultural awareness or knowledge, rather meta-cultural competence, which is required of an AI system. We lay out the principles of meta-cultural competence AI systems, and discuss ways to measure and model those.
  arXiv  Detail & Related papers  (2025-02-09T04:51:59Z)
• Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditions [9.357186653223332]
  We evaluate the capacity of Large Language Models to recognize and accurately respond to the Little Traditions within Indian society.<n>Through a series of case studies, we assess whether LLMs can balance the interplay between dominant Great Traditions and localized Little Traditions.<n>Our findings reveal that while LLMs demonstrate an ability to articulate cultural nuances, they often struggle to apply this understanding in practical, context-specific scenarios.
  arXiv  Detail & Related papers  (2025-01-28T06:58:25Z)
• Large Language Models Reflect the Ideology of their Creators [73.25935570218375]
  Large language models (LLMs) are trained on vast amounts of data to generate natural language. We uncover notable diversity in the ideological stance exhibited across different LLMs and languages.
  arXiv  Detail & Related papers  (2024-10-24T04:02:30Z)
• Are Large Language Models Ready for Travel Planning? [6.307444995285539]
  Large language models (LLMs) show promise in hospitality and tourism, their ability to provide unbiased service across demographic groups remains unclear. This paper explores gender and ethnic biases when LLMs are utilized as travel planning assistants.
  arXiv  Detail & Related papers  (2024-10-22T18:08:25Z)
• Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models [50.40276881893513]
  This study introduces Spoken Stereoset, a dataset specifically designed to evaluate social biases in Speech Large Language Models (SLLMs) By examining how different models respond to speech from diverse demographic groups, we aim to identify these biases. The findings indicate that while most models show minimal bias, some still exhibit slightly stereotypical or anti-stereotypical tendencies.
  arXiv  Detail & Related papers  (2024-08-14T16:55:06Z)
• Generative Monoculture in Large Language Models [17.164060958337032]
  generative monoculture is a behavior observed in large language models (LLMs) We experimentally demonstrate the prevalence of generative monoculture through analysis of book review and code generation tasks.
  arXiv  Detail & Related papers  (2024-07-02T12:17:07Z)
• See It from My Perspective: Diagnosing the Western Cultural Bias of Large Vision-Language Models in Image Understanding [78.88461026069862]
  Vision-language models (VLMs) can respond to queries about images in many languages. We present a novel investigation that demonstrates and localizes Western bias in image understanding.
  arXiv  Detail & Related papers  (2024-06-17T15:49:51Z)
• Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes [73.12947922129261]
  We leverage the zero-shot capabilities of large language models to reduce stereotyping. We show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups. We hope this work opens inquiry into other zero-shot techniques for bias mitigation.
  arXiv  Detail & Related papers  (2024-02-03T01:40:11Z)
• Finetuning an LLM on Contextual Knowledge of Classics for Q&A [0.0]
  This project is an attempt to merge the knowledge of Classics with the capabilities of artificial intelligence. The goal of this project is to develop an LLM that not only reproduces contextual knowledge accurately but also exhibits a consistent "personality"
  arXiv  Detail & Related papers  (2023-12-13T02:32:01Z)
• On the steerability of large language models toward data-driven personas [98.9138902560793]
  Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs.
  arXiv  Detail & Related papers  (2023-11-08T19:01:13Z)
• Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale [61.555788332182395]
  We investigate the potential for machine learning models to amplify dangerous and complex stereotypes. We find a broad range of ordinary prompts produce stereotypes, including prompts simply mentioning traits, descriptors, occupations, or objects.
  arXiv  Detail & Related papers  (2022-11-07T18:31:07Z)
• Whose Opinions Matter? Perspective-aware Models to Identify Opinions of Hate Speech Victims in Abusive Language Detection [6.167830237917662]
  We present an in-depth study to model polarized opinions coming from different communities. We believe that by relying on this information, we can divide the annotators into groups sharing similar perspectives. We propose a novel resource, a multi-perspective English language dataset annotated according to different sub-categories relevant for characterising online abuse.
  arXiv  Detail & Related papers  (2021-06-30T08:35:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.