pith:UV5JZQBY
Cross-Cultural Value Attribution in Large Vision-Language Models
Large vision-language models adjust their judgments of a person's moral, ethical, and political values when the same individual appears in different cultural contexts.
arxiv:2604.09945 v2 · 2026-04-10 · cs.CV · cs.AI · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{UV5JZQBYAZP2LL44E6ICGDGILT}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Our evaluation framework diagnoses LVLM awareness of cultural value differences through the use of Moral Foundations Theory, lexical analyses, and the sensitivity of generated values to depicted cultural contexts.
That counterfactual image sets successfully isolate cultural context effects without confounding visual factors, and that shifts in model outputs reflect internalized cultural value awareness rather than prompt artifacts or superficial associations.
LVLMs exhibit sensitivity to depicted cultural contexts when generating value judgments, diagnosed via Moral Foundations Theory, lexical analysis, and counterfactual image sets.
Receipt and verification
| First computed | 2026-07-03T01:16:53.172805Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
a57a9cc038065fa5af9c2790230cc85ce73ac58d5080808835c9e139e0e633d8
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/UV5JZQBYAZP2LL44E6ICGDGILT \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: a57a9cc038065fa5af9c2790230cc85ce73ac58d5080808835c9e139e0e633d8
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "17ee80bdb110a88e024ee0b5e55a611d3aefe2d75f99168fd8fef9505c47074a",
"cross_cats_sorted": [
"cs.AI",
"cs.CL"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-10T22:53:41Z",
"title_canon_sha256": "9f0c194f784e25be2aa17f3e827f41f8eda520e0b97b020446835cbf7487459a"
},
"schema_version": "1.0",
"source": {
"id": "2604.09945",
"kind": "arxiv",
"version": 2
}
}