pith:CHLSQ2OO
Diagnosing Korean-Language LLM Political Bias via Census-Grounded Agent Simulation
Census-grounded agent simulations diagnose political biases in Korean LLMs and accurately predict real election outcomes.
arxiv:2605.18395 v1 · 2026-05-18 · cs.CY · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{CHLSQ2OOEZL3LSZTTAXEIPZEHU}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Dynamo-K accurately predicts 3/3 presidential winners including a 2.1%p MAE on the 2022 race with 0.73%p margin and correctly identifies the dominant party in a held-out local election.
The assumption that census-grounded agent profiles and scenario prompts produce voter behavior distributions that are sufficiently representative of actual Korean electorate responses for the purpose of diagnosing model bias.
Dynamo-K is a census-grounded agent simulation that diagnoses three failure modes in Korean LLMs' political predictions and shows calibration methods that improve accuracy on historical elections.
References
Receipt and verification
| First computed | 2026-05-20T00:05:58.616595Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
11d72869ce2657b5cb33982e443f243d3fc4f806b538b5cb90d3f78b691e3949
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CHLSQ2OOEZL3LSZTTAXEIPZEHU \
| 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: 11d72869ce2657b5cb33982e443f243d3fc4f806b538b5cb90d3f78b691e3949
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "98f74b1801f553bf8e9dd8e336c256def41a25c7e608dbb0daa1f48ecc03c03e",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CY",
"submitted_at": "2026-05-18T13:42:23Z",
"title_canon_sha256": "63ae9df0108577604fcc866616e6d8d8bde6fc79acdb9cb68a1ae9126537009f"
},
"schema_version": "1.0",
"source": {
"id": "2605.18395",
"kind": "arxiv",
"version": 1
}
}