Researchers analyzed the epistemic diversity of LLMs (meaning: how many different positions/kinds of information do they produce for a given input). Result:
"every system is less diverse than a search baseline. This gap is not uniform: RAG can improve diversity, while large models are counterintuitively less diverse than smaller ones. Moreover, LLM parametric knowledge systematically reflects English over local-language knowledge for country specific topics."
https://arxiv.org/abs/2510.04226
tante
npub1de…gtq8a
2026-10-02 10:02:40 UTC
Author Public Key
npub1dedm8axlwewsysrxlw93kz43j6mgwf4cpync9gu8e95cl5za3s6s4gtq8aSeen on
wss://relay.mostr.pubPublished at
2026-10-02 10:02:40 UTCEvent JSON
{
"id": "37ad482ecd49f1e89383ba2a079228ab1824d1dac1ac7fec8287352e44033147",
"pubkey": "6e5bb3f4df765d024066fb8b1b0ab196b68726b8092782a387c9698fd05d8c35",
"created_at": 1790935360,
"kind": 1,
"tags": [
[
"proxy",
"https://tldr.nettime.org/users/tante/statuses/117370739806233108",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub"
]
],
"content": "Researchers analyzed the epistemic diversity of LLMs (meaning: how many different positions/kinds of information do they produce for a given input). Result:\n\n\"every system is less diverse than a search baseline. This gap is not uniform: RAG can improve diversity, while large models are counterintuitively less diverse than smaller ones. Moreover, LLM parametric knowledge systematically reflects English over local-language knowledge for country specific topics.\"\n\nhttps://arxiv.org/abs/2510.04226",
"sig": "76c0291734bd0b48f05492c74c2b7440d66494a3ef6d35dfcb9366d9fc4bee444fc314816de01b2b9c2e030b94146037372fa973673cabddc0398da3ec301751"
}