{
  "id": 4498,
  "url": "https://arxiv.org/abs/2605.11679v2",
  "title": "Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion",
  "summary": "In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tension between competing goals dictates that aggressively optimizing for one metric (e.g., helpfulness) frequently incurs a substantial penalty on another (e.g., harmlessness). While prior work mainly focuses on data selection, parameter merging, or algorithmic balancing during training, these approaches merely force compr",
  "authors": "ShiYing Huang, Liang Lin, Yuer Li, Kaiwen Luo, Zhenhong Zhou, An Zhang et al.",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-12T07:38:59.000Z",
  "fetched_at": "2026-07-14T16:31:03.578Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4498",
  "original_url": "https://arxiv.org/abs/2605.11679v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}