cd /news/large-language-models/which-india-survives-translation-nar… · home topics large-language-models article
[ARTICLE · art-113790] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Which India Survives Translation? Narrative Homogenisation Across Indian Oral Traditions in LLMs

A pilot computational study from arXiv (2608.26123v1) found that large language models (LLMs) partially homogenize Indian oral traditions, with cross-tradition similarity scores of 0.52-0.66 across the Rajasthani Pabuji epic, classical Tamil Sangam poetry, and Bengali folk tales. Prompting in regional languages (Hindi, Tamil, Bengali) reduced fidelity to authentic traditions by up to 27 percentage points compared to English prompting, according to the study's authors.

read1 min views3 publishedAug 28, 2026

arXiv:2608.26123v1 Announce Type: new Abstract: Large language models (LLMs) are trained predominantly on English-language internet text that over-represents certain cultural narratives, raising concerns that models flatten the diversity of non-Western storytelling traditions into a single homogenized archetype. We present a pilot computational study examining this across three maximally distinct Indian regional oral and literary traditions: the Rajasthani Pabuji epic, classical Tamil Sangam poetry, and Bengali folk tales. We collected authentic reference corpora for each tradition (11, 21, and 10 passages respectively) and prompted two LLMs (Claude Sonnet and Gemini) with 54 generation requests spanning three prompt types per tradition - generic, culturally specific, and regional-language. Using Sentence-BERT embeddings and cosine similarity, we measure reference drift (how closely outputs track their own tradition's authentic texts relative to the other two) and cross-tradition convergence (how similar outputs are across traditions). We find that while outputs remain closer to their own tradition's reference than to others, cross-tradition similarity is high (0.52-0.66) relative to what the traditions' genuine distance would predict, indicating partial homogenisation. Unexpectedly, prompting in the regional language (Hindi, Tamil, or Bengali) consistently reduced fidelity to the authentic tradition relative to English prompting, by as much as 27 percentage points for Rajasthani and Bengali traditions. We discuss this against conflicting prior results on multilingual prompting and argue it reflects a difference between eliciting general cultural diversity and simulating one narrow, lesser-documented oral tradition. We position this pilot as a lightweight, scalable complement to recent large-scale human-annotation studies of Indian cultural misrepresentation in LLM-generated stories, as part of a broader doctoral research program.

── more in #large-language-models 4 stories · sorted by recency
── more on @arxiv 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/which-india-survives…] indexed:0 read:1min 2026-08-28 ·