{
  "id": 7190,
  "url": "https://arxiv.org/abs/2604.06210v4",
  "title": "Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook",
  "summary": "As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks face the Construct-Composition-Context ($C^3$) challenge: relying on discriminative, multiple-choice formats that probe value knowledge rather than true orientations, overlook subcultural heterogeneity, and mismatch with real-world open-ended generation. We introduce DOVE, a distributional evaluation framework that directly compares human-written text",
  "authors": "Jaehyeok Lee, Xiaoyuan Yi, Jing Yao, Hyunjin Hwang, Roy Ka-Wei Lee, Xing Xie et al.",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-16T08:33:10.000Z",
  "fetched_at": "2026-07-14T16:33:03.572Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7190",
  "original_url": "https://arxiv.org/abs/2604.06210v4",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}