When Cow Urine Cures Constipation on YouTube: Limits of LLMs in Detecting Culture-specific Health Misinformation

• URL: http://arxiv.org/abs/2604.22002v1
• Date: Thu, 23 Apr 2026 18:42:37 GMT
• Title: When Cow Urine Cures Constipation on YouTube: Limits of LLMs in Detecting Culture-specific Health Misinformation
• Abstract summary: Using gomutra (cow urine) discourse on YouTube in India as a case study, we present a post-facto Large Language Model (LLM)-assisted discourse analysis.<n>We show that promotional content blends sacred traditional language with pseudo-scientific claims in ways that sophisticated debunking content itself mirrors.<n>Our findings argue that cultural competency in LLM-assisted discourse analysis cannot be retrofitted through prompt engineering alone.
• Score: 2.4751701576209166
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Social media platforms have become primary channels for health information in the Global South. Using gomutra (cow urine) discourse on YouTube in India as a case study, we present a post-facto Large Language Model (LLM)-assisted discourse analysis of 30 multilingual transcripts showing that promotional content blends sacred traditional language with pseudo-scientific claims in ways that sophisticated debunking content itself mirrors, creating a rhetorical register that LLMs, trained predominantly on Western corpora, are systematically ill-equipped to analyse. Varying prompt tone across three LLMs (GPT-4o, Gemini 2.5 Pro, DeepSeek-V3.1), we find that culturally embedded health misinformation does not look like ordinary misinformation, and this cultural obfuscation extends to gendered rhetoric and prompt design, compounding analytical unreliability. Our findings argue that cultural competency in LLM-assisted discourse analysis cannot be retrofitted through prompt engineering alone.

Related papers

• Dharma, Data and Deception: An LLM-Powered Rhetorical Analysis of Cow-Urine Health Claims on YouTube [2.4751701576209166]
  We examine 100 YouTube transcripts that promote or debunk cow urine (gomutra) as a health remedy.<n>We employ large language models (LLMs) including GPT-4, GPT-4o, GPT-4.1, GPT-5, Gemini 2.5 Pro, and Mistral Medium 3 to annotate transcripts.<n>Our analysis reveals that promoters predominantly rely on efficacy appeals and social proof, while debunkers emphasize authority and rebuttal.
  arXiv  Detail & Related papers  (2026-04-24T14:31:53Z)
• Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs [0.9021349761461702]
  We propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ)<n>The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan.<n>Our results suggest that the first clear signs appear after supervised fine-tuning, and not during pre-training.
  arXiv  Detail & Related papers  (2026-04-23T15:00:05Z)
• CURVE: A Benchmark for Cultural and Multilingual Long Video Reasoning [58.73855961335903]
  CURVE (Cultural Understanding and Reasoning in Video Evaluation) is a challenging benchmark for multicultural and multilingual video reasoning.<n>It comprises high-quality, entirely human-generated annotations from diverse, region-specific cultural videos across 18 global locales.<n>Our evaluations reveal that SoTA Video-LLMs struggle significantly, performing substantially below human-level accuracy.
  arXiv  Detail & Related papers  (2026-01-15T18:15:06Z)
• Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translation [70.43884512651668]
  We formalize Genette's (1987) theory of paratexts from literary and translation studies to introduce the task of paratextual explicitation for machine translation.<n>We construct a dataset of 560 expert-aligned paratexts from four English translations of the classical Chinese short story collection Liaozhai.<n>Our findings demonstrate the potential of paratextual explicitation in advancing machine translation beyond linguistic equivalence.
  arXiv  Detail & Related papers  (2025-09-27T16:27:36Z)
• How Much Content Do LLMs Generate That Induces Cognitive Bias in Users? [13.872175096831343]
  Large language models (LLMs) are increasingly integrated into applications ranging from review summarization to medical diagnosis support.<n>We investigate when and how LLMs expose users to biased content and quantify its severity.<n>Our findings show that LLMs expose users to content that changes the sentiment of the context in 21.86% of the cases, hallucinates on post-knowledge-cutoff data questions in 57.33% of the cases, and primacy bias in 5.94% of the cases.
  arXiv  Detail & Related papers  (2025-07-03T21:56:44Z)
• From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs [62.9861554207279]
  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>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)
• LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation [13.018071368511507]
  Non-native moderators struggle with interpreting culturally-specific knowledge, sentiment, and internet culture in hate speech moderation.<n>Our system achieves 78% accuracy, while reducing human workload by 83.6%.<n>Our findings suggest that non-native moderators, when properly supported by LLMs, can effectively contribute to cross-cultural hate speech moderation.
  arXiv  Detail & Related papers  (2025-03-10T12:20:20Z)
• Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense [98.09670425244462]
  Large language models (LLMs) have demonstrated substantial commonsense understanding. This paper examines the capabilities and limitations of several state-of-the-art LLMs in the context of cultural commonsense tasks.
  arXiv  Detail & Related papers  (2024-05-07T20:28:34Z)
• DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection [50.805599761583444]
  Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles. We propose Dell that identifies three key stages in misinformation detection where LLMs could be incorporated as part of the pipeline.
  arXiv  Detail & Related papers  (2024-02-16T03:24:56Z)
• A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models [7.705767540805267]
  Large Language Models (LLMs) continue to advance in their ability to write human-like text. A key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded. This paper presents a survey of over 32 techniques developed to mitigate hallucination in LLMs.
  arXiv  Detail & Related papers  (2024-01-02T17:56:30Z)
• Cross-Lingual Knowledge Editing in Large Language Models [73.12622532088564]
  Knowledge editing has been shown to adapt large language models to new knowledge without retraining from scratch. It is still unknown the effect of source language editing on a different target language. We first collect a large-scale cross-lingual synthetic dataset by translating ZsRE from English to Chinese.
  arXiv  Detail & Related papers  (2023-09-16T11:07:52Z)

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.